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

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

Neuron 3472 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 8.5370. Min Range: -8.5370

Max Act: 8.5370. Min Act: -0.0000

Data Index: 486650 (C4 (Web Text))

Max Activating Token Index: 70

Text #1

Max Range: 8.5370. Min Range: -8.5370

Max Act: 8.3257. Min Act: -0.0000

Data Index: 39353 (C4 (Web Text))

Max Activating Token Index: 419

Text #2

Max Range: 8.5370. Min Range: -8.5370

Max Act: 8.2251. Min Act: -0.0000

Data Index: 279590 (C4 (Web Text))

Max Activating Token Index: 192

Text #3

Max Range: 8.5370. Min Range: -8.5370

Max Act: 7.9533. Min Act: -0.0000

Data Index: 242719 (C4 (Web Text))

Max Activating Token Index: 224

Text #4

Max Range: 8.5370. Min Range: -8.5370

Max Act: 8.1038. Min Act: -0.0000

Data Index: 779997 (C4 (Web Text))

Max Activating Token Index: 523

Text #5

Max Range: 8.5370. Min Range: -8.5370

Max Act: 8.2815. Min Act: -0.0000

Data Index: 575864 (C4 (Web Text))

Max Activating Token Index: 61

Text #6

Max Range: 8.5370. Min Range: -8.5370

Max Act: 7.8852. Min Act: -0.0000

Data Index: 815594 (C4 (Web Text))

Max Activating Token Index: 823

Text #7

Max Range: 8.5370. Min Range: -8.5370

Max Act: 7.8252. Min Act: -0.0000

Data Index: 910380 (C4 (Web Text))

Max Activating Token Index: 94

Text #8

Max Range: 8.5370. Min Range: -8.5370

Max Act: 7.9971. Min Act: -0.0000

Data Index: 380919 (C4 (Web Text))

Max Activating Token Index: 193

Text #9

Max Range: 8.5370. Min Range: -8.5370

Max Act: 7.3596. Min Act: -0.0000

Data Index: 52257 (C4 (Web Text))

Max Activating Token Index: 207

Text #10

Max Range: 8.5370. Min Range: -8.5370

Max Act: 7.9211. Min Act: -0.0000

Data Index: 1173541 (C4 (Web Text))

Max Activating Token Index: 102

Text #11

Max Range: 8.5370. Min Range: -8.5370

Max Act: 7.7263. Min Act: -0.0000

Data Index: 1011448 (C4 (Web Text))

Max Activating Token Index: 421

Text #12

Max Range: 8.5370. Min Range: -8.5370

Max Act: 7.7114. Min Act: -0.0000

Data Index: 1193274 (C4 (Web Text))

Max Activating Token Index: 799

Text #13

Max Range: 8.5370. Min Range: -8.5370

Max Act: 7.7973. Min Act: -0.0000

Data Index: 799663 (C4 (Web Text))

Max Activating Token Index: 601

Text #14

Max Range: 8.5370. Min Range: -8.5370

Max Act: 7.5634. Min Act: -0.0000

Data Index: 616344 (C4 (Web Text))

Max Activating Token Index: 424

Text #15

Max Range: 8.5370. Min Range: -8.5370

Max Act: 7.5563. Min Act: -0.0000

Data Index: 151244 (C4 (Web Text))

Max Activating Token Index: 810

Text #16

Max Range: 8.5370. Min Range: -8.5370

Max Act: 7.6994. Min Act: -0.0000

Data Index: 1110847 (C4 (Web Text))

Max Activating Token Index: 971

Text #17

Max Range: 8.5370. Min Range: -8.5370

Max Act: 7.3654. Min Act: -0.0000

Data Index: 319478 (C4 (Web Text))

Max Activating Token Index: 706

Text #18

Max Range: 8.5370. Min Range: -8.5370

Max Act: 7.3001. Min Act: -0.0000

Data Index: 985510 (C4 (Web Text))

Max Activating Token Index: 400

Text #19

Max Range: 8.5370. Min Range: -8.5370

Max Act: 7.2531. Min Act: -0.0000

Data Index: 259190 (C4 (Web Text))

Max Activating Token Index: 727