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

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

Neuron 1151 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: 0.0462. Min Range: -0.0462

Max Act: 0.0462. Min Act: -0.0003

Data Index: 203895 (C4 (Web Text))

Max Activating Token Index: 921

Text #1

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0459. Min Act: -0.0003

Data Index: 1346895 (C4 (Web Text))

Max Activating Token Index: 571

Text #2

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0448. Min Act: -0.0003

Data Index: 1160880 (C4 (Web Text))

Max Activating Token Index: 72

Text #3

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0428. Min Act: -0.0003

Data Index: 69996 (C4 (Web Text))

Max Activating Token Index: 897

Text #4

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0422. Min Act: -0.0003

Data Index: 428472 (C4 (Web Text))

Max Activating Token Index: 425

Text #5

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0404. Min Act: -0.0003

Data Index: 1176125 (C4 (Web Text))

Max Activating Token Index: 647

Text #6

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0372. Min Act: -0.0003

Data Index: 421383 (C4 (Web Text))

Max Activating Token Index: 338

Text #7

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0391. Min Act: -0.0002

Data Index: 768238 (C4 (Web Text))

Max Activating Token Index: 820

Text #8

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0383. Min Act: -0.0003

Data Index: 915974 (C4 (Web Text))

Max Activating Token Index: 88

Text #9

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0364. Min Act: -0.0003

Data Index: 878725 (C4 (Web Text))

Max Activating Token Index: 714

Text #10

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0370. Min Act: -0.0003

Data Index: 1198941 (C4 (Web Text))

Max Activating Token Index: 973

Text #11

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0390. Min Act: -0.0003

Data Index: 831940 (C4 (Web Text))

Max Activating Token Index: 381

Text #12

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0373. Min Act: -0.0003

Data Index: 62488 (C4 (Web Text))

Max Activating Token Index: 925

Text #13

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0368. Min Act: -0.0003

Data Index: 739425 (C4 (Web Text))

Max Activating Token Index: 204

Text #14

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0354. Min Act: -0.0003

Data Index: 1127645 (C4 (Web Text))

Max Activating Token Index: 774

Text #15

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0346. Min Act: -0.0004

Data Index: 320185 (C4 (Web Text))

Max Activating Token Index: 285

Text #16

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0339. Min Act: -0.0003

Data Index: 702949 (C4 (Web Text))

Max Activating Token Index: 558

Text #17

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0358. Min Act: -0.0003

Data Index: 586770 (C4 (Web Text))

Max Activating Token Index: 130

Text #18

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0345. Min Act: -0.0002

Data Index: 567055 (C4 (Web Text))

Max Activating Token Index: 543

Text #19

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0344. Min Act: -0.0003

Data Index: 380890 (C4 (Web Text))

Max Activating Token Index: 587