< Prev | Home | Model | Random | Next >

Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 5119 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')



Text #0

Max Range: 3.2970. Min Range: -3.2970

Max Act: 3.2970. Min Act: -0.0000

Data Index: 1918345 (The Pile)

Max Activating Token Index: 1017

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 3.2970. Min Range: -3.2970

Max Act: 3.0314. Min Act: -0.0000

Data Index: 809415 (The Pile)

Max Activating Token Index: 116

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 3.2970. Min Range: -3.2970

Max Act: 2.8886. Min Act: -0.0000

Data Index: 1111072 (The Pile)

Max Activating Token Index: 63

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 3.2970. Min Range: -3.2970

Max Act: 2.8197. Min Act: -0.0000

Data Index: 245456 (The Pile)

Max Activating Token Index: 503

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 3.2970. Min Range: -3.2970

Max Act: 2.7996. Min Act: -0.0000

Data Index: 64693 (The Pile)

Max Activating Token Index: 873

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 3.2970. Min Range: -3.2970

Max Act: 2.7731. Min Act: -0.0000

Data Index: 1475603 (The Pile)

Max Activating Token Index: 86

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 3.2970. Min Range: -3.2970

Max Act: 2.6006. Min Act: -0.0000

Data Index: 958587 (The Pile)

Max Activating Token Index: 784

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 3.2970. Min Range: -3.2970

Max Act: 2.7369. Min Act: -0.0000

Data Index: 1515943 (The Pile)

Max Activating Token Index: 48

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 3.2970. Min Range: -3.2970

Max Act: 2.4964. Min Act: -0.0000

Data Index: 1022488 (The Pile)

Max Activating Token Index: 891

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 3.2970. Min Range: -3.2970

Max Act: 2.5456. Min Act: -0.0000

Data Index: 1502026 (The Pile)

Max Activating Token Index: 181

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 3.2970. Min Range: -3.2970

Max Act: 2.5487. Min Act: -0.0000

Data Index: 1229191 (The Pile)

Max Activating Token Index: 179

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 3.2970. Min Range: -3.2970

Max Act: 2.7058. Min Act: -0.0000

Data Index: 1872281 (The Pile)

Max Activating Token Index: 574

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 3.2970. Min Range: -3.2970

Max Act: 2.5248. Min Act: -0.0000

Data Index: 684517 (The Pile)

Max Activating Token Index: 229

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 3.2970. Min Range: -3.2970

Max Act: 2.6569. Min Act: -0.0000

Data Index: 1928012 (The Pile)

Max Activating Token Index: 426

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 3.2970. Min Range: -3.2970

Max Act: 2.5053. Min Act: -0.0000

Data Index: 976626 (The Pile)

Max Activating Token Index: 440

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 3.2970. Min Range: -3.2970

Max Act: 2.7682. Min Act: -0.0000

Data Index: 1176771 (The Pile)

Max Activating Token Index: 344

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 3.2970. Min Range: -3.2970

Max Act: 2.8126. Min Act: -0.0000

Data Index: 1049310 (The Pile)

Max Activating Token Index: 908

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 3.2970. Min Range: -3.2970

Max Act: 2.9431. Min Act: -0.0000

Data Index: 807594 (The Pile)

Max Activating Token Index: 739

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 3.2970. Min Range: -3.2970

Max Act: 2.6451. Min Act: -0.0000

Data Index: 854802 (The Pile)

Max Activating Token Index: 378

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 3.2970. Min Range: -3.2970

Max Act: 2.4788. Min Act: -0.0000

Data Index: 1948311 (The Pile)

Max Activating Token Index: 710

Click toggle to see full text

Truncated

Full Text #19