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

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

Neuron 4468 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1129. Min Range: -2.1129

Max Act: 2.1129. Min Act: -0.0000

Data Index: 626420 (C4 (Web Text))

Max Activating Token Index: 17

Text #1

Max Range: 2.1129. Min Range: -2.1129

Max Act: 1.9922. Min Act: -0.0000

Data Index: 1234749 (C4 (Web Text))

Max Activating Token Index: 259

Text #2

Max Range: 2.1129. Min Range: -2.1129

Max Act: 1.8206. Min Act: -0.0000

Data Index: 1202503 (C4 (Web Text))

Max Activating Token Index: 14

Text #3

Max Range: 2.1129. Min Range: -2.1129

Max Act: 1.8616. Min Act: -0.0000

Data Index: 690375 (C4 (Web Text))

Max Activating Token Index: 438

Text #4

Max Range: 2.1129. Min Range: -2.1129

Max Act: 1.9102. Min Act: -0.0000

Data Index: 529618 (C4 (Web Text))

Max Activating Token Index: 84

Text #5

Max Range: 2.1129. Min Range: -2.1129

Max Act: 1.7916. Min Act: -0.0000

Data Index: 1111048 (C4 (Web Text))

Max Activating Token Index: 925

Text #6

Max Range: 2.1129. Min Range: -2.1129

Max Act: 1.8625. Min Act: -0.0000

Data Index: 988545 (C4 (Web Text))

Max Activating Token Index: 287

Text #7

Max Range: 2.1129. Min Range: -2.1129

Max Act: 1.7514. Min Act: -0.0000

Data Index: 1029601 (C4 (Web Text))

Max Activating Token Index: 97

Text #8

Max Range: 2.1129. Min Range: -2.1129

Max Act: 1.7016. Min Act: -0.0000

Data Index: 205635 (C4 (Web Text))

Max Activating Token Index: 820

Text #9

Max Range: 2.1129. Min Range: -2.1129

Max Act: 1.6973. Min Act: -0.0000

Data Index: 277204 (C4 (Web Text))

Max Activating Token Index: 474

Text #10

Max Range: 2.1129. Min Range: -2.1129

Max Act: 1.6789. Min Act: -0.0000

Data Index: 63879 (C4 (Web Text))

Max Activating Token Index: 55

Text #11

Max Range: 2.1129. Min Range: -2.1129

Max Act: 1.5322. Min Act: -0.0000

Data Index: 1125000 (C4 (Web Text))

Max Activating Token Index: 21

Text #12

Max Range: 2.1129. Min Range: -2.1129

Max Act: 1.6929. Min Act: -0.0000

Data Index: 974920 (C4 (Web Text))

Max Activating Token Index: 91

Text #13

Max Range: 2.1129. Min Range: -2.1129

Max Act: 1.6662. Min Act: -0.0000

Data Index: 648712 (C4 (Web Text))

Max Activating Token Index: 252

Text #14

Max Range: 2.1129. Min Range: -2.1129

Max Act: 1.5787. Min Act: -0.0000

Data Index: 691499 (C4 (Web Text))

Max Activating Token Index: 220

Text #15

Max Range: 2.1129. Min Range: -2.1129

Max Act: 1.5780. Min Act: -0.0000

Data Index: 196976 (C4 (Web Text))

Max Activating Token Index: 33

Text #16

Max Range: 2.1129. Min Range: -2.1129

Max Act: 1.5559. Min Act: -0.0000

Data Index: 878560 (C4 (Web Text))

Max Activating Token Index: 574

Text #17

Max Range: 2.1129. Min Range: -2.1129

Max Act: 1.5587. Min Act: -0.0000

Data Index: 1204541 (C4 (Web Text))

Max Activating Token Index: 75

Text #18

Max Range: 2.1129. Min Range: -2.1129

Max Act: 1.5445. Min Act: -0.0000

Data Index: 413141 (C4 (Web Text))

Max Activating Token Index: 23

Text #19

Max Range: 2.1129. Min Range: -2.1129

Max Act: 1.4433. Min Act: -0.0000

Data Index: 349810 (C4 (Web Text))

Max Activating Token Index: 48