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

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

Neuron 62 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7249. Min Range: -0.7249

Max Act: 0.7249. Min Act: -0.0000

Data Index: 222592 (C4 (Web Text))

Max Activating Token Index: 338

Text #1

Max Range: 0.7249. Min Range: -0.7249

Max Act: 0.5060. Min Act: -0.0000

Data Index: 1304471 (C4 (Web Text))

Max Activating Token Index: 716

Text #2

Max Range: 0.7249. Min Range: -0.7249

Max Act: 0.5062. Min Act: -0.0000

Data Index: 1386934 (Python Code)

Max Activating Token Index: 40

Text #3

Max Range: 0.7249. Min Range: -0.7249

Max Act: 0.5055. Min Act: -0.0000

Data Index: 1227135 (C4 (Web Text))

Max Activating Token Index: 660

Text #4

Max Range: 0.7249. Min Range: -0.7249

Max Act: 0.5217. Min Act: -0.0000

Data Index: 483803 (C4 (Web Text))

Max Activating Token Index: 817

Text #5

Max Range: 0.7249. Min Range: -0.7249

Max Act: 0.4924. Min Act: -0.0000

Data Index: 1171320 (C4 (Web Text))

Max Activating Token Index: 179

Text #6

Max Range: 0.7249. Min Range: -0.7249

Max Act: 0.5321. Min Act: -0.0000

Data Index: 1121560 (C4 (Web Text))

Max Activating Token Index: 851

Text #7

Max Range: 0.7249. Min Range: -0.7249

Max Act: 0.4601. Min Act: -0.0000

Data Index: 897260 (C4 (Web Text))

Max Activating Token Index: 676

Text #8

Max Range: 0.7249. Min Range: -0.7249

Max Act: 0.4476. Min Act: -0.0000

Data Index: 1572659 (Python Code)

Max Activating Token Index: 248

Text #9

Max Range: 0.7249. Min Range: -0.7249

Max Act: 0.4495. Min Act: -0.0000

Data Index: 1438295 (Python Code)

Max Activating Token Index: 284

Text #10

Max Range: 0.7249. Min Range: -0.7249

Max Act: 0.4109. Min Act: -0.0000

Data Index: 435338 (C4 (Web Text))

Max Activating Token Index: 619

Text #11

Max Range: 0.7249. Min Range: -0.7249

Max Act: 0.4113. Min Act: -0.0000

Data Index: 1623639 (Python Code)

Max Activating Token Index: 127

Text #12

Max Range: 0.7249. Min Range: -0.7249

Max Act: 0.4264. Min Act: -0.0000

Data Index: 1448273 (Python Code)

Max Activating Token Index: 175

Text #13

Max Range: 0.7249. Min Range: -0.7249

Max Act: 0.4113. Min Act: -0.0000

Data Index: 1604540 (Python Code)

Max Activating Token Index: 925

Text #14

Max Range: 0.7249. Min Range: -0.7249

Max Act: 0.4245. Min Act: -0.0000

Data Index: 830094 (C4 (Web Text))

Max Activating Token Index: 833

Text #15

Max Range: 0.7249. Min Range: -0.7249

Max Act: 0.4040. Min Act: -0.0000

Data Index: 1600564 (Python Code)

Max Activating Token Index: 988

Text #16

Max Range: 0.7249. Min Range: -0.7249

Max Act: 0.4050. Min Act: -0.0000

Data Index: 1538081 (Python Code)

Max Activating Token Index: 796

Text #17

Max Range: 0.7249. Min Range: -0.7249

Max Act: 0.3752. Min Act: -0.0000

Data Index: 617569 (C4 (Web Text))

Max Activating Token Index: 170

Text #18

Max Range: 0.7249. Min Range: -0.7249

Max Act: 0.3969. Min Act: -0.0000

Data Index: 1636761 (Python Code)

Max Activating Token Index: 563

Text #19

Max Range: 0.7249. Min Range: -0.7249

Max Act: 0.3828. Min Act: -0.0000

Data Index: 1520666 (Python Code)

Max Activating Token Index: 336