< Prev | Home | Model | Random | Next >

Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: The Pile

Neuron 3055 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')



Text #0

Max Range: 0.6667. Min Range: -0.6667

Max Act: 0.6667. Min Act: -0.0001

Data Index: 713337 (The Pile)

Max Activating Token Index: 530

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 0.6667. Min Range: -0.6667

Max Act: 0.6039. Min Act: -0.0001

Data Index: 1302827 (The Pile)

Max Activating Token Index: 26

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 0.6667. Min Range: -0.6667

Max Act: 0.6146. Min Act: -0.0001

Data Index: 496550 (The Pile)

Max Activating Token Index: 701

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 0.6667. Min Range: -0.6667

Max Act: 0.6121. Min Act: -0.0001

Data Index: 1086867 (The Pile)

Max Activating Token Index: 113

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 0.6667. Min Range: -0.6667

Max Act: 0.5568. Min Act: -0.0001

Data Index: 753805 (The Pile)

Max Activating Token Index: 26

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 0.6667. Min Range: -0.6667

Max Act: 0.5382. Min Act: -0.0001

Data Index: 400552 (The Pile)

Max Activating Token Index: 317

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 0.6667. Min Range: -0.6667

Max Act: 0.5519. Min Act: -0.0001

Data Index: 543041 (The Pile)

Max Activating Token Index: 670

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 0.6667. Min Range: -0.6667

Max Act: 0.5147. Min Act: -0.0001

Data Index: 4529 (The Pile)

Max Activating Token Index: 139

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 0.6667. Min Range: -0.6667

Max Act: 0.4862. Min Act: -0.0001

Data Index: 1417321 (The Pile)

Max Activating Token Index: 145

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 0.6667. Min Range: -0.6667

Max Act: 0.5353. Min Act: -0.0001

Data Index: 1485380 (The Pile)

Max Activating Token Index: 673

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 0.6667. Min Range: -0.6667

Max Act: 0.4699. Min Act: -0.0001

Data Index: 1835246 (The Pile)

Max Activating Token Index: 284

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 0.6667. Min Range: -0.6667

Max Act: 0.5087. Min Act: -0.0001

Data Index: 1104910 (The Pile)

Max Activating Token Index: 526

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 0.6667. Min Range: -0.6667

Max Act: 0.5084. Min Act: -0.0001

Data Index: 414620 (The Pile)

Max Activating Token Index: 426

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 0.6667. Min Range: -0.6667

Max Act: 0.4259. Min Act: -0.0001

Data Index: 1283584 (The Pile)

Max Activating Token Index: 163

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 0.6667. Min Range: -0.6667

Max Act: 0.5103. Min Act: -0.0001

Data Index: 1663270 (The Pile)

Max Activating Token Index: 877

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 0.6667. Min Range: -0.6667

Max Act: 0.5051. Min Act: -0.0001

Data Index: 1125057 (The Pile)

Max Activating Token Index: 700

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 0.6667. Min Range: -0.6667

Max Act: 0.4096. Min Act: -0.0001

Data Index: 1404473 (The Pile)

Max Activating Token Index: 109

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 0.6667. Min Range: -0.6667

Max Act: 0.4485. Min Act: -0.0001

Data Index: 1246079 (The Pile)

Max Activating Token Index: 316

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 0.6667. Min Range: -0.6667

Max Act: 0.4930. Min Act: -0.0001

Data Index: 1337546 (The Pile)

Max Activating Token Index: 924

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 0.6667. Min Range: -0.6667

Max Act: 0.3612. Min Act: -0.0000

Data Index: 1522292 (The Pile)

Max Activating Token Index: 62

Click toggle to see full text

Truncated

Full Text #19