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

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

Neuron 5874 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: 2.3959. Min Range: -2.3959

Max Act: 2.3959. Min Act: -0.0000

Data Index: 1245420 (C4 (Web Text))

Max Activating Token Index: 462

Text #1

Max Range: 2.3959. Min Range: -2.3959

Max Act: 1.4519. Min Act: -0.0000

Data Index: 836255 (C4 (Web Text))

Max Activating Token Index: 587

Text #2

Max Range: 2.3959. Min Range: -2.3959

Max Act: 1.3794. Min Act: -0.0000

Data Index: 773519 (C4 (Web Text))

Max Activating Token Index: 113

Text #3

Max Range: 2.3959. Min Range: -2.3959

Max Act: 1.3185. Min Act: -0.0000

Data Index: 1331288 (C4 (Web Text))

Max Activating Token Index: 159

Text #4

Max Range: 2.3959. Min Range: -2.3959

Max Act: 1.1761. Min Act: -0.0000

Data Index: 279780 (C4 (Web Text))

Max Activating Token Index: 349

Text #5

Max Range: 2.3959. Min Range: -2.3959

Max Act: 1.0665. Min Act: -0.0000

Data Index: 1098288 (C4 (Web Text))

Max Activating Token Index: 827

Text #6

Max Range: 2.3959. Min Range: -2.3959

Max Act: 1.1060. Min Act: -0.0000

Data Index: 360151 (C4 (Web Text))

Max Activating Token Index: 147

Text #7

Max Range: 2.3959. Min Range: -2.3959

Max Act: 1.0614. Min Act: -0.0000

Data Index: 1204373 (C4 (Web Text))

Max Activating Token Index: 727

Text #8

Max Range: 2.3959. Min Range: -2.3959

Max Act: 1.1350. Min Act: -0.0000

Data Index: 12129 (C4 (Web Text))

Max Activating Token Index: 31

Text #9

Max Range: 2.3959. Min Range: -2.3959

Max Act: 1.0944. Min Act: -0.0000

Data Index: 1276475 (C4 (Web Text))

Max Activating Token Index: 823

Text #10

Max Range: 2.3959. Min Range: -2.3959

Max Act: 1.1287. Min Act: -0.0000

Data Index: 940460 (C4 (Web Text))

Max Activating Token Index: 802

Text #11

Max Range: 2.3959. Min Range: -2.3959

Max Act: 1.0107. Min Act: -0.0000

Data Index: 591989 (C4 (Web Text))

Max Activating Token Index: 539

Text #12

Max Range: 2.3959. Min Range: -2.3959

Max Act: 0.9282. Min Act: -0.0000

Data Index: 938822 (C4 (Web Text))

Max Activating Token Index: 196

Text #13

Max Range: 2.3959. Min Range: -2.3959

Max Act: 1.0503. Min Act: -0.0000

Data Index: 834093 (C4 (Web Text))

Max Activating Token Index: 499

Text #14

Max Range: 2.3959. Min Range: -2.3959

Max Act: 0.9823. Min Act: -0.0000

Data Index: 383683 (C4 (Web Text))

Max Activating Token Index: 238

Text #15

Max Range: 2.3959. Min Range: -2.3959

Max Act: 1.0228. Min Act: -0.0000

Data Index: 242042 (C4 (Web Text))

Max Activating Token Index: 725

Text #16

Max Range: 2.3959. Min Range: -2.3959

Max Act: 1.0478. Min Act: -0.0000

Data Index: 883062 (C4 (Web Text))

Max Activating Token Index: 640

Text #17

Max Range: 2.3959. Min Range: -2.3959

Max Act: 1.0258. Min Act: -0.0000

Data Index: 830544 (C4 (Web Text))

Max Activating Token Index: 39

Text #18

Max Range: 2.3959. Min Range: -2.3959

Max Act: 0.9953. Min Act: -0.0000

Data Index: 648773 (C4 (Web Text))

Max Activating Token Index: 272

Text #19

Max Range: 2.3959. Min Range: -2.3959

Max Act: 1.0362. Min Act: -0.0000

Data Index: 1077982 (C4 (Web Text))

Max Activating Token Index: 667