Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 389 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0420. Min Act: -0.0003

Data Index: 884795 (C4 (Web Text))

Max Activating Token Index: 880

Text #1

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0391. Min Act: -0.0003

Data Index: 203087 (C4 (Web Text))

Max Activating Token Index: 211

Text #2

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0394. Min Act: -0.0003

Data Index: 100394 (C4 (Web Text))

Max Activating Token Index: 422

Text #3

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0377. Min Act: -0.0003

Data Index: 1244096 (C4 (Web Text))

Max Activating Token Index: 179

Text #4

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0401. Min Act: -0.0003

Data Index: 1318728 (C4 (Web Text))

Max Activating Token Index: 425

Text #5

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0381. Min Act: -0.0004

Data Index: 44736 (C4 (Web Text))

Max Activating Token Index: 223

Text #6

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0323. Min Act: -0.0003

Data Index: 125426 (C4 (Web Text))

Max Activating Token Index: 955

Text #7

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0402. Min Act: -0.0003

Data Index: 116405 (C4 (Web Text))

Max Activating Token Index: 88

Text #8

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0392. Min Act: -0.0004

Data Index: 1192673 (C4 (Web Text))

Max Activating Token Index: 662

Text #9

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0379. Min Act: -0.0003

Data Index: 369888 (C4 (Web Text))

Max Activating Token Index: 181

Text #10

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0371. Min Act: -0.0003

Data Index: 8871 (C4 (Web Text))

Max Activating Token Index: 77

Text #11

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0363. Min Act: -0.0003

Data Index: 492302 (C4 (Web Text))

Max Activating Token Index: 468

Text #12

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0389. Min Act: -0.0003

Data Index: 49193 (C4 (Web Text))

Max Activating Token Index: 626

Text #13

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0380. Min Act: -0.0003

Data Index: 452122 (C4 (Web Text))

Max Activating Token Index: 99

Text #14

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0382. Min Act: -0.0004

Data Index: 1021059 (C4 (Web Text))

Max Activating Token Index: 826

Text #15

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0367. Min Act: -0.0004

Data Index: 898942 (C4 (Web Text))

Max Activating Token Index: 849

Text #16

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0380. Min Act: -0.0003

Data Index: 577679 (C4 (Web Text))

Max Activating Token Index: 494

Text #17

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0381. Min Act: -0.0003

Data Index: 1334087 (C4 (Web Text))

Max Activating Token Index: 774

Text #18

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0379. Min Act: -0.0003

Data Index: 986499 (C4 (Web Text))

Max Activating Token Index: 148

Text #19

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0370. Min Act: -0.0003

Data Index: 1169711 (C4 (Web Text))

Max Activating Token Index: 534