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

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

Neuron 4559 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: 1.7326. Min Range: -1.7326

Max Act: 1.7326. Min Act: -0.0000

Data Index: 973288 (C4 (Web Text))

Max Activating Token Index: 547

Text #1

Max Range: 1.7326. Min Range: -1.7326

Max Act: 1.6264. Min Act: -0.0000

Data Index: 53021 (C4 (Web Text))

Max Activating Token Index: 616

Text #2

Max Range: 1.7326. Min Range: -1.7326

Max Act: 1.6151. Min Act: -0.0000

Data Index: 580617 (C4 (Web Text))

Max Activating Token Index: 702

Text #3

Max Range: 1.7326. Min Range: -1.7326

Max Act: 1.6034. Min Act: -0.0000

Data Index: 632204 (C4 (Web Text))

Max Activating Token Index: 508

Text #4

Max Range: 1.7326. Min Range: -1.7326

Max Act: 1.6885. Min Act: -0.0000

Data Index: 1335422 (C4 (Web Text))

Max Activating Token Index: 858

Text #5

Max Range: 1.7326. Min Range: -1.7326

Max Act: 1.5938. Min Act: -0.0000

Data Index: 1151969 (C4 (Web Text))

Max Activating Token Index: 441

Text #6

Max Range: 1.7326. Min Range: -1.7326

Max Act: 1.6916. Min Act: -0.0000

Data Index: 173478 (C4 (Web Text))

Max Activating Token Index: 669

Text #7

Max Range: 1.7326. Min Range: -1.7326

Max Act: 1.4878. Min Act: -0.0000

Data Index: 414995 (C4 (Web Text))

Max Activating Token Index: 779

Text #8

Max Range: 1.7326. Min Range: -1.7326

Max Act: 1.3759. Min Act: -0.0000

Data Index: 41682 (C4 (Web Text))

Max Activating Token Index: 436

Text #9

Max Range: 1.7326. Min Range: -1.7326

Max Act: 1.3698. Min Act: -0.0000

Data Index: 1355269 (C4 (Web Text))

Max Activating Token Index: 291

Text #10

Max Range: 1.7326. Min Range: -1.7326

Max Act: 1.3401. Min Act: -0.0000

Data Index: 717407 (C4 (Web Text))

Max Activating Token Index: 639

Text #11

Max Range: 1.7326. Min Range: -1.7326

Max Act: 1.4315. Min Act: -0.0000

Data Index: 14328 (C4 (Web Text))

Max Activating Token Index: 926

Text #12

Max Range: 1.7326. Min Range: -1.7326

Max Act: 1.4126. Min Act: -0.0000

Data Index: 255472 (C4 (Web Text))

Max Activating Token Index: 894

Text #13

Max Range: 1.7326. Min Range: -1.7326

Max Act: 1.3531. Min Act: -0.0000

Data Index: 1138302 (C4 (Web Text))

Max Activating Token Index: 169

Text #14

Max Range: 1.7326. Min Range: -1.7326

Max Act: 1.3563. Min Act: -0.0000

Data Index: 382949 (C4 (Web Text))

Max Activating Token Index: 630

Text #15

Max Range: 1.7326. Min Range: -1.7326

Max Act: 1.3259. Min Act: -0.0000

Data Index: 446126 (C4 (Web Text))

Max Activating Token Index: 630

Text #16

Max Range: 1.7326. Min Range: -1.7326

Max Act: 1.4153. Min Act: -0.0000

Data Index: 805354 (C4 (Web Text))

Max Activating Token Index: 999

Text #17

Max Range: 1.7326. Min Range: -1.7326

Max Act: 1.3038. Min Act: -0.0000

Data Index: 260239 (C4 (Web Text))

Max Activating Token Index: 90

Text #18

Max Range: 1.7326. Min Range: -1.7326

Max Act: 1.3288. Min Act: -0.0000

Data Index: 182655 (C4 (Web Text))

Max Activating Token Index: 930

Text #19

Max Range: 1.7326. Min Range: -1.7326

Max Act: 1.3386. Min Act: -0.0000

Data Index: 23410 (C4 (Web Text))

Max Activating Token Index: 995