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

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

Neuron 1581 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0391. Min Act: -0.0006

Data Index: 194702 (C4 (Web Text))

Max Activating Token Index: 602

Text #1

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0364. Min Act: -0.0006

Data Index: 1182141 (C4 (Web Text))

Max Activating Token Index: 411

Text #2

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0361. Min Act: -0.0006

Data Index: 1105631 (C4 (Web Text))

Max Activating Token Index: 808

Text #3

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0350. Min Act: -0.0006

Data Index: 578879 (C4 (Web Text))

Max Activating Token Index: 214

Text #4

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0356. Min Act: -0.0006

Data Index: 829418 (C4 (Web Text))

Max Activating Token Index: 684

Text #5

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0353. Min Act: -0.0006

Data Index: 799072 (C4 (Web Text))

Max Activating Token Index: 551

Text #6

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0343. Min Act: -0.0006

Data Index: 276440 (C4 (Web Text))

Max Activating Token Index: 194

Text #7

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0340. Min Act: -0.0006

Data Index: 262905 (C4 (Web Text))

Max Activating Token Index: 44

Text #8

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0329. Min Act: -0.0006

Data Index: 1263705 (C4 (Web Text))

Max Activating Token Index: 73

Text #9

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0333. Min Act: -0.0005

Data Index: 861835 (C4 (Web Text))

Max Activating Token Index: 587

Text #10

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0333. Min Act: -0.0006

Data Index: 695041 (C4 (Web Text))

Max Activating Token Index: 355

Text #11

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0333. Min Act: -0.0006

Data Index: 465875 (C4 (Web Text))

Max Activating Token Index: 652

Text #12

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0339. Min Act: -0.0006

Data Index: 796868 (C4 (Web Text))

Max Activating Token Index: 464

Text #13

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0323. Min Act: -0.0006

Data Index: 704407 (C4 (Web Text))

Max Activating Token Index: 469

Text #14

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0328. Min Act: -0.0006

Data Index: 1126575 (C4 (Web Text))

Max Activating Token Index: 205

Text #15

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0326. Min Act: -0.0006

Data Index: 330123 (C4 (Web Text))

Max Activating Token Index: 579

Text #16

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0325. Min Act: -0.0006

Data Index: 71300 (C4 (Web Text))

Max Activating Token Index: 586

Text #17

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0325. Min Act: -0.0006

Data Index: 403521 (C4 (Web Text))

Max Activating Token Index: 477

Text #18

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0318. Min Act: -0.0006

Data Index: 739693 (C4 (Web Text))

Max Activating Token Index: 545

Text #19

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0326. Min Act: -0.0006

Data Index: 625437 (C4 (Web Text))

Max Activating Token Index: 560