Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1263 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.3554. Min Range: -0.3554

Max Act: 0.3346. Min Act: -0.0003

Data Index: 492837 (C4 (Web Text))

Max Activating Token Index: 187

Text #1

Max Range: 0.3554. Min Range: -0.3554

Max Act: 0.3407. Min Act: -0.0003

Data Index: 61260 (C4 (Web Text))

Max Activating Token Index: 258

Text #2

Max Range: 0.3554. Min Range: -0.3554

Max Act: 0.3541. Min Act: -0.0003

Data Index: 432689 (C4 (Web Text))

Max Activating Token Index: 423

Text #3

Max Range: 0.3554. Min Range: -0.3554

Max Act: 0.3548. Min Act: -0.0003

Data Index: 972155 (C4 (Web Text))

Max Activating Token Index: 72

Text #4

Max Range: 0.3554. Min Range: -0.3554

Max Act: 0.3377. Min Act: -0.0003

Data Index: 434406 (C4 (Web Text))

Max Activating Token Index: 88

Text #5

Max Range: 0.3554. Min Range: -0.3554

Max Act: 0.3554. Min Act: -0.0003

Data Index: 726471 (C4 (Web Text))

Max Activating Token Index: 359

Text #6

Max Range: 0.3554. Min Range: -0.3554

Max Act: 0.3357. Min Act: -0.0003

Data Index: 111943 (C4 (Web Text))

Max Activating Token Index: 64

Text #7

Max Range: 0.3554. Min Range: -0.3554

Max Act: 0.3447. Min Act: -0.0003

Data Index: 977046 (C4 (Web Text))

Max Activating Token Index: 345

Text #8

Max Range: 0.3554. Min Range: -0.3554

Max Act: 0.3261. Min Act: -0.0003

Data Index: 397328 (C4 (Web Text))

Max Activating Token Index: 363

Text #9

Max Range: 0.3554. Min Range: -0.3554

Max Act: 0.3307. Min Act: -0.0003

Data Index: 1041316 (C4 (Web Text))

Max Activating Token Index: 648

Text #10

Max Range: 0.3554. Min Range: -0.3554

Max Act: 0.3251. Min Act: -0.0003

Data Index: 437795 (C4 (Web Text))

Max Activating Token Index: 190

Text #11

Max Range: 0.3554. Min Range: -0.3554

Max Act: 0.3398. Min Act: -0.0003

Data Index: 614562 (C4 (Web Text))

Max Activating Token Index: 97

Text #12

Max Range: 0.3554. Min Range: -0.3554

Max Act: 0.3166. Min Act: -0.0003

Data Index: 337964 (C4 (Web Text))

Max Activating Token Index: 401

Text #13

Max Range: 0.3554. Min Range: -0.3554

Max Act: 0.3315. Min Act: -0.0003

Data Index: 743614 (C4 (Web Text))

Max Activating Token Index: 298

Text #14

Max Range: 0.3554. Min Range: -0.3554

Max Act: 0.3363. Min Act: -0.0003

Data Index: 631508 (C4 (Web Text))

Max Activating Token Index: 289

Text #15

Max Range: 0.3554. Min Range: -0.3554

Max Act: 0.3383. Min Act: -0.0003

Data Index: 898083 (C4 (Web Text))

Max Activating Token Index: 201

Text #16

Max Range: 0.3554. Min Range: -0.3554

Max Act: 0.3222. Min Act: -0.0003

Data Index: 476648 (C4 (Web Text))

Max Activating Token Index: 84

Text #17

Max Range: 0.3554. Min Range: -0.3554

Max Act: 0.3187. Min Act: -0.0003

Data Index: 142690 (C4 (Web Text))

Max Activating Token Index: 205

Text #18

Max Range: 0.3554. Min Range: -0.3554

Max Act: 0.3183. Min Act: -0.0003

Data Index: 176912 (C4 (Web Text))

Max Activating Token Index: 598

Text #19

Max Range: 0.3554. Min Range: -0.3554

Max Act: 0.3323. Min Act: -0.0003

Data Index: 1200647 (C4 (Web Text))

Max Activating Token Index: 58