Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4845 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 7.6192. Min Range: -7.6192

Max Act: 7.6192. Min Act: -0.0000

Data Index: 563679 (C4 (Web Text))

Max Activating Token Index: 569

Text #1

Max Range: 7.6192. Min Range: -7.6192

Max Act: 6.7956. Min Act: -0.0000

Data Index: 239007 (C4 (Web Text))

Max Activating Token Index: 242

Text #2

Max Range: 7.6192. Min Range: -7.6192

Max Act: 5.5548. Min Act: -0.0000

Data Index: 133049 (C4 (Web Text))

Max Activating Token Index: 135

Text #3

Max Range: 7.6192. Min Range: -7.6192

Max Act: 5.3051. Min Act: -0.0000

Data Index: 92329 (C4 (Web Text))

Max Activating Token Index: 223

Text #4

Max Range: 7.6192. Min Range: -7.6192

Max Act: 5.2976. Min Act: -0.0000

Data Index: 1464117 (Python Code)

Max Activating Token Index: 856

Text #5

Max Range: 7.6192. Min Range: -7.6192

Max Act: 5.3203. Min Act: -0.0000

Data Index: 666712 (C4 (Web Text))

Max Activating Token Index: 657

Text #6

Max Range: 7.6192. Min Range: -7.6192

Max Act: 4.9339. Min Act: -0.0000

Data Index: 423495 (C4 (Web Text))

Max Activating Token Index: 634

Text #7

Max Range: 7.6192. Min Range: -7.6192

Max Act: 4.7108. Min Act: -0.0000

Data Index: 1194897 (C4 (Web Text))

Max Activating Token Index: 883

Text #8

Max Range: 7.6192. Min Range: -7.6192

Max Act: 4.7166. Min Act: -0.0000

Data Index: 30534 (C4 (Web Text))

Max Activating Token Index: 860

Text #9

Max Range: 7.6192. Min Range: -7.6192

Max Act: 4.5421. Min Act: -0.0000

Data Index: 263681 (C4 (Web Text))

Max Activating Token Index: 910

Text #10

Max Range: 7.6192. Min Range: -7.6192

Max Act: 4.6150. Min Act: -0.0000

Data Index: 808715 (C4 (Web Text))

Max Activating Token Index: 469

Text #11

Max Range: 7.6192. Min Range: -7.6192

Max Act: 4.7091. Min Act: -0.0000

Data Index: 825023 (C4 (Web Text))

Max Activating Token Index: 32

Text #12

Max Range: 7.6192. Min Range: -7.6192

Max Act: 4.8925. Min Act: -0.0000

Data Index: 106980 (C4 (Web Text))

Max Activating Token Index: 228

Text #13

Max Range: 7.6192. Min Range: -7.6192

Max Act: 4.4902. Min Act: -0.0000

Data Index: 433737 (C4 (Web Text))

Max Activating Token Index: 807

Text #14

Max Range: 7.6192. Min Range: -7.6192

Max Act: 4.8483. Min Act: -0.0000

Data Index: 352290 (C4 (Web Text))

Max Activating Token Index: 653

Text #15

Max Range: 7.6192. Min Range: -7.6192

Max Act: 4.8337. Min Act: -0.0000

Data Index: 27928 (C4 (Web Text))

Max Activating Token Index: 267

Text #16

Max Range: 7.6192. Min Range: -7.6192

Max Act: 5.0301. Min Act: -0.0000

Data Index: 398704 (C4 (Web Text))

Max Activating Token Index: 522

Text #17

Max Range: 7.6192. Min Range: -7.6192

Max Act: 4.5859. Min Act: -0.0000

Data Index: 1032267 (C4 (Web Text))

Max Activating Token Index: 109

Text #18

Max Range: 7.6192. Min Range: -7.6192

Max Act: 4.9671. Min Act: -0.0000

Data Index: 1488948 (Python Code)

Max Activating Token Index: 1006

Text #19

Max Range: 7.6192. Min Range: -7.6192

Max Act: 4.7162. Min Act: -0.0000

Data Index: 1305021 (C4 (Web Text))

Max Activating Token Index: 690