< Prev | Home | Model | Random | Next >

Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 41 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')



Text #0

Max Range: 1.7254. Min Range: -1.7254

Max Act: 1.5788. Min Act: -0.0001

Data Index: 686918 (The Pile)

Max Activating Token Index: 629

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 1.7254. Min Range: -1.7254

Max Act: 1.6863. Min Act: -0.0000

Data Index: 448806 (The Pile)

Max Activating Token Index: 13

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 1.7254. Min Range: -1.7254

Max Act: 1.7254. Min Act: -0.0001

Data Index: 903862 (The Pile)

Max Activating Token Index: 162

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 1.7254. Min Range: -1.7254

Max Act: 1.5108. Min Act: -0.0001

Data Index: 801471 (The Pile)

Max Activating Token Index: 170

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 1.7254. Min Range: -1.7254

Max Act: 1.6897. Min Act: -0.0000

Data Index: 598317 (The Pile)

Max Activating Token Index: 46

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 1.7254. Min Range: -1.7254

Max Act: 1.5877. Min Act: -0.0001

Data Index: 1692431 (The Pile)

Max Activating Token Index: 535

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 1.7254. Min Range: -1.7254

Max Act: 1.3361. Min Act: -0.0001

Data Index: 1174215 (The Pile)

Max Activating Token Index: 948

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 1.7254. Min Range: -1.7254

Max Act: 1.3891. Min Act: -0.0001

Data Index: 1006327 (The Pile)

Max Activating Token Index: 964

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 1.7254. Min Range: -1.7254

Max Act: 1.5171. Min Act: -0.0001

Data Index: 888732 (The Pile)

Max Activating Token Index: 963

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 1.7254. Min Range: -1.7254

Max Act: 1.4978. Min Act: -0.0001

Data Index: 1242166 (The Pile)

Max Activating Token Index: 355

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 1.7254. Min Range: -1.7254

Max Act: 1.4327. Min Act: -0.0001

Data Index: 164093 (The Pile)

Max Activating Token Index: 831

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 1.7254. Min Range: -1.7254

Max Act: 1.6138. Min Act: -0.0001

Data Index: 1711344 (The Pile)

Max Activating Token Index: 336

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 1.7254. Min Range: -1.7254

Max Act: 1.3256. Min Act: -0.0001

Data Index: 1209227 (The Pile)

Max Activating Token Index: 620

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 1.7254. Min Range: -1.7254

Max Act: 1.4304. Min Act: -0.0001

Data Index: 1231602 (The Pile)

Max Activating Token Index: 932

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 1.7254. Min Range: -1.7254

Max Act: 1.5292. Min Act: -0.0001

Data Index: 1113296 (The Pile)

Max Activating Token Index: 139

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 1.7254. Min Range: -1.7254

Max Act: 1.5539. Min Act: -0.0001

Data Index: 788667 (The Pile)

Max Activating Token Index: 1018

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 1.7254. Min Range: -1.7254

Max Act: 1.4354. Min Act: -0.0001

Data Index: 1702044 (The Pile)

Max Activating Token Index: 895

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 1.7254. Min Range: -1.7254

Max Act: 1.3129. Min Act: -0.0001

Data Index: 339759 (The Pile)

Max Activating Token Index: 746

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 1.7254. Min Range: -1.7254

Max Act: 1.5677. Min Act: -0.0001

Data Index: 505072 (The Pile)

Max Activating Token Index: 943

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 1.7254. Min Range: -1.7254

Max Act: 1.4075. Min Act: -0.0001

Data Index: 378026 (The Pile)

Max Activating Token Index: 910

Click toggle to see full text

Truncated

Full Text #19