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

Dataset: The Pile

Neuron 299 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4145. Min Range: -0.4145

Max Act: 0.4112. Min Act: -0.0000

Data Index: 1271916 (The Pile)

Max Activating Token Index: 279

Text #1

Max Range: 0.4145. Min Range: -0.4145

Max Act: 0.4145. Min Act: -0.0000

Data Index: 1844798 (The Pile)

Max Activating Token Index: 768

Text #2

Max Range: 0.4145. Min Range: -0.4145

Max Act: 0.3303. Min Act: -0.0000

Data Index: 103665 (The Pile)

Max Activating Token Index: 110

Text #3

Max Range: 0.4145. Min Range: -0.4145

Max Act: 0.3383. Min Act: -0.0000

Data Index: 83081 (The Pile)

Max Activating Token Index: 664

Text #4

Max Range: 0.4145. Min Range: -0.4145

Max Act: 0.3283. Min Act: -0.0000

Data Index: 1346963 (The Pile)

Max Activating Token Index: 603

Text #5

Max Range: 0.4145. Min Range: -0.4145

Max Act: 0.3046. Min Act: -0.0000

Data Index: 516014 (The Pile)

Max Activating Token Index: 303

Text #6

Max Range: 0.4145. Min Range: -0.4145

Max Act: 0.3151. Min Act: -0.0000

Data Index: 906084 (The Pile)

Max Activating Token Index: 954

Text #7

Max Range: 0.4145. Min Range: -0.4145

Max Act: 0.3064. Min Act: -0.0000

Data Index: 1293195 (The Pile)

Max Activating Token Index: 191

Text #8

Max Range: 0.4145. Min Range: -0.4145

Max Act: 0.3262. Min Act: -0.0000

Data Index: 808380 (The Pile)

Max Activating Token Index: 360

Text #9

Max Range: 0.4145. Min Range: -0.4145

Max Act: 0.3255. Min Act: -0.0000

Data Index: 573966 (The Pile)

Max Activating Token Index: 293

Text #10

Max Range: 0.4145. Min Range: -0.4145

Max Act: 0.3023. Min Act: -0.0000

Data Index: 272323 (The Pile)

Max Activating Token Index: 319

Text #11

Max Range: 0.4145. Min Range: -0.4145

Max Act: 0.3126. Min Act: -0.0000

Data Index: 472406 (The Pile)

Max Activating Token Index: 345

Text #12

Max Range: 0.4145. Min Range: -0.4145

Max Act: 0.3219. Min Act: -0.0000

Data Index: 36847 (The Pile)

Max Activating Token Index: 504

Text #13

Max Range: 0.4145. Min Range: -0.4145

Max Act: 0.3001. Min Act: -0.0000

Data Index: 176674 (The Pile)

Max Activating Token Index: 206

Text #14

Max Range: 0.4145. Min Range: -0.4145

Max Act: 0.3083. Min Act: -0.0000

Data Index: 582569 (The Pile)

Max Activating Token Index: 495

Text #15

Max Range: 0.4145. Min Range: -0.4145

Max Act: 0.3443. Min Act: -0.0000

Data Index: 431189 (The Pile)

Max Activating Token Index: 731

Text #16

Max Range: 0.4145. Min Range: -0.4145

Max Act: 0.2983. Min Act: -0.0000

Data Index: 1294857 (The Pile)

Max Activating Token Index: 371

Text #17

Max Range: 0.4145. Min Range: -0.4145

Max Act: 0.3295. Min Act: -0.0000

Data Index: 594059 (The Pile)

Max Activating Token Index: 33

Text #18

Max Range: 0.4145. Min Range: -0.4145

Max Act: 0.3041. Min Act: -0.0000

Data Index: 1388610 (The Pile)

Max Activating Token Index: 576

Text #19

Max Range: 0.4145. Min Range: -0.4145

Max Act: 0.2872. Min Act: -0.0000

Data Index: 1425192 (The Pile)

Max Activating Token Index: 591