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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 2336 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.3313. Min Range: -7.3313

Max Act: 7.3313. Min Act: -0.0000

Data Index: 493882 (C4 (Web Text))

Max Activating Token Index: 336

Text #1

Max Range: 7.3313. Min Range: -7.3313

Max Act: 6.6964. Min Act: -0.0000

Data Index: 547007 (C4 (Web Text))

Max Activating Token Index: 306

Text #2

Max Range: 7.3313. Min Range: -7.3313

Max Act: 6.6081. Min Act: -0.0000

Data Index: 455939 (C4 (Web Text))

Max Activating Token Index: 982

Text #3

Max Range: 7.3313. Min Range: -7.3313

Max Act: 6.2628. Min Act: -0.0000

Data Index: 611907 (C4 (Web Text))

Max Activating Token Index: 489

Text #4

Max Range: 7.3313. Min Range: -7.3313

Max Act: 6.0737. Min Act: -0.0000

Data Index: 272019 (C4 (Web Text))

Max Activating Token Index: 931

Text #5

Max Range: 7.3313. Min Range: -7.3313

Max Act: 5.9666. Min Act: -0.0000

Data Index: 1144480 (C4 (Web Text))

Max Activating Token Index: 273

Text #6

Max Range: 7.3313. Min Range: -7.3313

Max Act: 5.9421. Min Act: -0.0000

Data Index: 847680 (C4 (Web Text))

Max Activating Token Index: 171

Text #7

Max Range: 7.3313. Min Range: -7.3313

Max Act: 5.8409. Min Act: -0.0000

Data Index: 833969 (C4 (Web Text))

Max Activating Token Index: 846

Text #8

Max Range: 7.3313. Min Range: -7.3313

Max Act: 5.7316. Min Act: -0.0000

Data Index: 622387 (C4 (Web Text))

Max Activating Token Index: 615

Text #9

Max Range: 7.3313. Min Range: -7.3313

Max Act: 5.5246. Min Act: -0.0000

Data Index: 620704 (C4 (Web Text))

Max Activating Token Index: 190

Text #10

Max Range: 7.3313. Min Range: -7.3313

Max Act: 5.6043. Min Act: -0.0000

Data Index: 1198784 (C4 (Web Text))

Max Activating Token Index: 130

Text #11

Max Range: 7.3313. Min Range: -7.3313

Max Act: 5.5294. Min Act: -0.0000

Data Index: 828167 (C4 (Web Text))

Max Activating Token Index: 986

Text #12

Max Range: 7.3313. Min Range: -7.3313

Max Act: 5.3416. Min Act: -0.0000

Data Index: 281401 (C4 (Web Text))

Max Activating Token Index: 917

Text #13

Max Range: 7.3313. Min Range: -7.3313

Max Act: 5.2695. Min Act: -0.0000

Data Index: 1257911 (C4 (Web Text))

Max Activating Token Index: 983

Text #14

Max Range: 7.3313. Min Range: -7.3313

Max Act: 4.9561. Min Act: -0.0000

Data Index: 686453 (C4 (Web Text))

Max Activating Token Index: 18

Text #15

Max Range: 7.3313. Min Range: -7.3313

Max Act: 5.0446. Min Act: -0.0000

Data Index: 920126 (C4 (Web Text))

Max Activating Token Index: 198

Text #16

Max Range: 7.3313. Min Range: -7.3313

Max Act: 4.8446. Min Act: -0.0000

Data Index: 445888 (C4 (Web Text))

Max Activating Token Index: 774

Text #17

Max Range: 7.3313. Min Range: -7.3313

Max Act: 4.6205. Min Act: -0.0000

Data Index: 683866 (C4 (Web Text))

Max Activating Token Index: 43

Text #18

Max Range: 7.3313. Min Range: -7.3313

Max Act: 4.5055. Min Act: -0.0000

Data Index: 1063394 (C4 (Web Text))

Max Activating Token Index: 490

Text #19

Max Range: 7.3313. Min Range: -7.3313

Max Act: 4.6451. Min Act: -0.0000

Data Index: 383363 (C4 (Web Text))

Max Activating Token Index: 132