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

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

Neuron 235 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: 2.0232. Min Range: -2.0232

Max Act: 2.0232. Min Act: -0.0000

Data Index: 85375 (C4 (Web Text))

Max Activating Token Index: 529

Text #1

Max Range: 2.0232. Min Range: -2.0232

Max Act: 1.7834. Min Act: -0.0000

Data Index: 457169 (C4 (Web Text))

Max Activating Token Index: 449

Text #2

Max Range: 2.0232. Min Range: -2.0232

Max Act: 1.5853. Min Act: -0.0000

Data Index: 1274336 (C4 (Web Text))

Max Activating Token Index: 999

Text #3

Max Range: 2.0232. Min Range: -2.0232

Max Act: 1.3885. Min Act: -0.0000

Data Index: 1132571 (C4 (Web Text))

Max Activating Token Index: 807

Text #4

Max Range: 2.0232. Min Range: -2.0232

Max Act: 1.3204. Min Act: -0.0000

Data Index: 625649 (C4 (Web Text))

Max Activating Token Index: 409

Text #5

Max Range: 2.0232. Min Range: -2.0232

Max Act: 1.2866. Min Act: -0.0000

Data Index: 1185902 (C4 (Web Text))

Max Activating Token Index: 813

Text #6

Max Range: 2.0232. Min Range: -2.0232

Max Act: 1.2461. Min Act: -0.0000

Data Index: 1310876 (C4 (Web Text))

Max Activating Token Index: 339

Text #7

Max Range: 2.0232. Min Range: -2.0232

Max Act: 1.2451. Min Act: -0.0000

Data Index: 228510 (C4 (Web Text))

Max Activating Token Index: 620

Text #8

Max Range: 2.0232. Min Range: -2.0232

Max Act: 1.2173. Min Act: -0.0000

Data Index: 914438 (C4 (Web Text))

Max Activating Token Index: 789

Text #9

Max Range: 2.0232. Min Range: -2.0232

Max Act: 1.2466. Min Act: -0.0000

Data Index: 1094777 (C4 (Web Text))

Max Activating Token Index: 269

Text #10

Max Range: 2.0232. Min Range: -2.0232

Max Act: 1.2329. Min Act: -0.0000

Data Index: 26382 (C4 (Web Text))

Max Activating Token Index: 23

Text #11

Max Range: 2.0232. Min Range: -2.0232

Max Act: 1.1714. Min Act: -0.0000

Data Index: 394023 (C4 (Web Text))

Max Activating Token Index: 178

Text #12

Max Range: 2.0232. Min Range: -2.0232

Max Act: 1.1680. Min Act: -0.0000

Data Index: 312678 (C4 (Web Text))

Max Activating Token Index: 945

Text #13

Max Range: 2.0232. Min Range: -2.0232

Max Act: 1.0520. Min Act: -0.0000

Data Index: 577558 (C4 (Web Text))

Max Activating Token Index: 527

Text #14

Max Range: 2.0232. Min Range: -2.0232

Max Act: 1.0572. Min Act: -0.0000

Data Index: 535075 (C4 (Web Text))

Max Activating Token Index: 375

Text #15

Max Range: 2.0232. Min Range: -2.0232

Max Act: 1.1074. Min Act: -0.0000

Data Index: 155795 (C4 (Web Text))

Max Activating Token Index: 20

Text #16

Max Range: 2.0232. Min Range: -2.0232

Max Act: 1.0007. Min Act: -0.0000

Data Index: 1103478 (C4 (Web Text))

Max Activating Token Index: 74

Text #17

Max Range: 2.0232. Min Range: -2.0232

Max Act: 1.0752. Min Act: -0.0000

Data Index: 1043834 (C4 (Web Text))

Max Activating Token Index: 370

Text #18

Max Range: 2.0232. Min Range: -2.0232

Max Act: 1.0023. Min Act: -0.0000

Data Index: 1026289 (C4 (Web Text))

Max Activating Token Index: 848

Text #19

Max Range: 2.0232. Min Range: -2.0232

Max Act: 0.9966. Min Act: -0.0000

Data Index: 969098 (C4 (Web Text))

Max Activating Token Index: 614