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

Dataset: The Pile

Neuron 3039 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7189. Min Range: -1.7189

Max Act: 1.7189. Min Act: -0.0000

Data Index: 574960 (The Pile)

Max Activating Token Index: 180

Text #1

Max Range: 1.7189. Min Range: -1.7189

Max Act: 1.4111. Min Act: -0.0000

Data Index: 239147 (The Pile)

Max Activating Token Index: 524

Text #2

Max Range: 1.7189. Min Range: -1.7189

Max Act: 1.5081. Min Act: -0.0000

Data Index: 1227623 (The Pile)

Max Activating Token Index: 805

Text #3

Max Range: 1.7189. Min Range: -1.7189

Max Act: 1.4542. Min Act: -0.0000

Data Index: 1493267 (The Pile)

Max Activating Token Index: 89

Text #4

Max Range: 1.7189. Min Range: -1.7189

Max Act: 1.4496. Min Act: -0.0000

Data Index: 854307 (The Pile)

Max Activating Token Index: 385

Text #5

Max Range: 1.7189. Min Range: -1.7189

Max Act: 1.4398. Min Act: -0.0000

Data Index: 1354335 (The Pile)

Max Activating Token Index: 210

Text #6

Max Range: 1.7189. Min Range: -1.7189

Max Act: 1.3158. Min Act: -0.0000

Data Index: 148255 (The Pile)

Max Activating Token Index: 437

Text #7

Max Range: 1.7189. Min Range: -1.7189

Max Act: 1.4704. Min Act: -0.0000

Data Index: 1145580 (The Pile)

Max Activating Token Index: 76

Text #8

Max Range: 1.7189. Min Range: -1.7189

Max Act: 1.4346. Min Act: -0.0000

Data Index: 450611 (The Pile)

Max Activating Token Index: 826

Text #9

Max Range: 1.7189. Min Range: -1.7189

Max Act: 1.2811. Min Act: -0.0000

Data Index: 415077 (The Pile)

Max Activating Token Index: 964

Text #10

Max Range: 1.7189. Min Range: -1.7189

Max Act: 1.3357. Min Act: -0.0000

Data Index: 1369775 (The Pile)

Max Activating Token Index: 792

Text #11

Max Range: 1.7189. Min Range: -1.7189

Max Act: 1.3435. Min Act: -0.0000

Data Index: 490905 (The Pile)

Max Activating Token Index: 267

Text #12

Max Range: 1.7189. Min Range: -1.7189

Max Act: 1.1447. Min Act: -0.0000

Data Index: 200300 (The Pile)

Max Activating Token Index: 684

Text #13

Max Range: 1.7189. Min Range: -1.7189

Max Act: 1.1828. Min Act: -0.0000

Data Index: 1962545 (The Pile)

Max Activating Token Index: 654

Text #14

Max Range: 1.7189. Min Range: -1.7189

Max Act: 1.1939. Min Act: -0.0000

Data Index: 1871654 (The Pile)

Max Activating Token Index: 959

Text #15

Max Range: 1.7189. Min Range: -1.7189

Max Act: 1.1958. Min Act: -0.0000

Data Index: 1157249 (The Pile)

Max Activating Token Index: 907

Text #16

Max Range: 1.7189. Min Range: -1.7189

Max Act: 1.1559. Min Act: -0.0000

Data Index: 894646 (The Pile)

Max Activating Token Index: 449

Text #17

Max Range: 1.7189. Min Range: -1.7189

Max Act: 1.2206. Min Act: -0.0000

Data Index: 492232 (The Pile)

Max Activating Token Index: 280

Text #18

Max Range: 1.7189. Min Range: -1.7189

Max Act: 1.2209. Min Act: -0.0000

Data Index: 1471133 (The Pile)

Max Activating Token Index: 642

Text #19

Max Range: 1.7189. Min Range: -1.7189

Max Act: 1.1407. Min Act: -0.0000

Data Index: 1612190 (The Pile)

Max Activating Token Index: 695