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

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

Neuron 3907 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8875. Min Range: -1.8875

Max Act: 1.8218. Min Act: -0.0001

Data Index: 1311884 (C4 (Web Text))

Max Activating Token Index: 275

Text #1

Max Range: 1.8875. Min Range: -1.8875

Max Act: 1.8875. Min Act: -0.0000

Data Index: 81334 (C4 (Web Text))

Max Activating Token Index: 439

Text #2

Max Range: 1.8875. Min Range: -1.8875

Max Act: 1.6974. Min Act: -0.0000

Data Index: 720819 (C4 (Web Text))

Max Activating Token Index: 197

Text #3

Max Range: 1.8875. Min Range: -1.8875

Max Act: 1.6722. Min Act: -0.0000

Data Index: 910871 (C4 (Web Text))

Max Activating Token Index: 485

Text #4

Max Range: 1.8875. Min Range: -1.8875

Max Act: 1.5159. Min Act: -0.0000

Data Index: 829263 (C4 (Web Text))

Max Activating Token Index: 503

Text #5

Max Range: 1.8875. Min Range: -1.8875

Max Act: 1.3935. Min Act: -0.0001

Data Index: 994076 (C4 (Web Text))

Max Activating Token Index: 49

Text #6

Max Range: 1.8875. Min Range: -1.8875

Max Act: 1.3849. Min Act: -0.0000

Data Index: 563508 (C4 (Web Text))

Max Activating Token Index: 909

Text #7

Max Range: 1.8875. Min Range: -1.8875

Max Act: 1.3585. Min Act: -0.0000

Data Index: 676199 (C4 (Web Text))

Max Activating Token Index: 284

Text #8

Max Range: 1.8875. Min Range: -1.8875

Max Act: 1.4036. Min Act: -0.0000

Data Index: 847433 (C4 (Web Text))

Max Activating Token Index: 614

Text #9

Max Range: 1.8875. Min Range: -1.8875

Max Act: 1.4359. Min Act: -0.0000

Data Index: 924232 (C4 (Web Text))

Max Activating Token Index: 970

Text #10

Max Range: 1.8875. Min Range: -1.8875

Max Act: 1.3854. Min Act: -0.0000

Data Index: 48302 (C4 (Web Text))

Max Activating Token Index: 906

Text #11

Max Range: 1.8875. Min Range: -1.8875

Max Act: 1.3041. Min Act: -0.0000

Data Index: 717330 (C4 (Web Text))

Max Activating Token Index: 196

Text #12

Max Range: 1.8875. Min Range: -1.8875

Max Act: 1.2530. Min Act: -0.0000

Data Index: 433281 (C4 (Web Text))

Max Activating Token Index: 756

Text #13

Max Range: 1.8875. Min Range: -1.8875

Max Act: 1.1960. Min Act: -0.0000

Data Index: 32978 (C4 (Web Text))

Max Activating Token Index: 990

Text #14

Max Range: 1.8875. Min Range: -1.8875

Max Act: 1.2640. Min Act: -0.0000

Data Index: 1023367 (C4 (Web Text))

Max Activating Token Index: 469

Text #15

Max Range: 1.8875. Min Range: -1.8875

Max Act: 1.3335. Min Act: -0.0000

Data Index: 1271240 (C4 (Web Text))

Max Activating Token Index: 883

Text #16

Max Range: 1.8875. Min Range: -1.8875

Max Act: 1.2335. Min Act: -0.0001

Data Index: 898124 (C4 (Web Text))

Max Activating Token Index: 34

Text #17

Max Range: 1.8875. Min Range: -1.8875

Max Act: 1.2981. Min Act: -0.0000

Data Index: 502179 (C4 (Web Text))

Max Activating Token Index: 397

Text #18

Max Range: 1.8875. Min Range: -1.8875

Max Act: 1.1837. Min Act: -0.0000

Data Index: 47290 (C4 (Web Text))

Max Activating Token Index: 205

Text #19

Max Range: 1.8875. Min Range: -1.8875

Max Act: 1.1765. Min Act: -0.0000

Data Index: 1277864 (C4 (Web Text))

Max Activating Token Index: 836