Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2354 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.3216. Min Range: -1.3216

Max Act: 1.3023. Min Act: -0.0001

Data Index: 141951 (C4 (Web Text))

Max Activating Token Index: 154

Text #1

Max Range: 1.3216. Min Range: -1.3216

Max Act: 1.3216. Min Act: -0.0001

Data Index: 287775 (C4 (Web Text))

Max Activating Token Index: 288

Text #2

Max Range: 1.3216. Min Range: -1.3216

Max Act: 1.2073. Min Act: -0.0001

Data Index: 1027107 (C4 (Web Text))

Max Activating Token Index: 39

Text #3

Max Range: 1.3216. Min Range: -1.3216

Max Act: 1.1835. Min Act: -0.0001

Data Index: 513433 (C4 (Web Text))

Max Activating Token Index: 581

Text #4

Max Range: 1.3216. Min Range: -1.3216

Max Act: 1.0926. Min Act: -0.0001

Data Index: 117605 (C4 (Web Text))

Max Activating Token Index: 582

Text #5

Max Range: 1.3216. Min Range: -1.3216

Max Act: 1.0726. Min Act: -0.0001

Data Index: 593344 (C4 (Web Text))

Max Activating Token Index: 384

Text #6

Max Range: 1.3216. Min Range: -1.3216

Max Act: 1.1122. Min Act: -0.0001

Data Index: 1130176 (C4 (Web Text))

Max Activating Token Index: 397

Text #7

Max Range: 1.3216. Min Range: -1.3216

Max Act: 1.0005. Min Act: -0.0001

Data Index: 456110 (C4 (Web Text))

Max Activating Token Index: 812

Text #8

Max Range: 1.3216. Min Range: -1.3216

Max Act: 0.9300. Min Act: -0.0001

Data Index: 503923 (C4 (Web Text))

Max Activating Token Index: 685

Text #9

Max Range: 1.3216. Min Range: -1.3216

Max Act: 0.9460. Min Act: -0.0001

Data Index: 1199370 (C4 (Web Text))

Max Activating Token Index: 573

Text #10

Max Range: 1.3216. Min Range: -1.3216

Max Act: 0.9675. Min Act: -0.0001

Data Index: 579227 (C4 (Web Text))

Max Activating Token Index: 594

Text #11

Max Range: 1.3216. Min Range: -1.3216

Max Act: 1.0362. Min Act: -0.0001

Data Index: 394314 (C4 (Web Text))

Max Activating Token Index: 338

Text #12

Max Range: 1.3216. Min Range: -1.3216

Max Act: 0.9733. Min Act: -0.0001

Data Index: 628866 (C4 (Web Text))

Max Activating Token Index: 538

Text #13

Max Range: 1.3216. Min Range: -1.3216

Max Act: 0.9479. Min Act: -0.0001

Data Index: 1334171 (C4 (Web Text))

Max Activating Token Index: 891

Text #14

Max Range: 1.3216. Min Range: -1.3216

Max Act: 0.9323. Min Act: -0.0001

Data Index: 1314106 (C4 (Web Text))

Max Activating Token Index: 636

Text #15

Max Range: 1.3216. Min Range: -1.3216

Max Act: 1.0214. Min Act: -0.0001

Data Index: 502682 (C4 (Web Text))

Max Activating Token Index: 458

Text #16

Max Range: 1.3216. Min Range: -1.3216

Max Act: 0.9560. Min Act: -0.0001

Data Index: 573300 (C4 (Web Text))

Max Activating Token Index: 276

Text #17

Max Range: 1.3216. Min Range: -1.3216

Max Act: 0.9183. Min Act: -0.0001

Data Index: 355000 (C4 (Web Text))

Max Activating Token Index: 660

Text #18

Max Range: 1.3216. Min Range: -1.3216

Max Act: 0.9387. Min Act: -0.0001

Data Index: 890397 (C4 (Web Text))

Max Activating Token Index: 495

Text #19

Max Range: 1.3216. Min Range: -1.3216

Max Act: 0.9427. Min Act: -0.0001

Data Index: 993168 (C4 (Web Text))

Max Activating Token Index: 245