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

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

Neuron 2015 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: 0.0460. Min Range: -0.0460

Max Act: 0.0460. Min Act: -0.0004

Data Index: 518331 (C4 (Web Text))

Max Activating Token Index: 817

Text #1

Max Range: 0.0460. Min Range: -0.0460

Max Act: 0.0444. Min Act: -0.0003

Data Index: 899505 (C4 (Web Text))

Max Activating Token Index: 93

Text #2

Max Range: 0.0460. Min Range: -0.0460

Max Act: 0.0445. Min Act: -0.0002

Data Index: 1104384 (C4 (Web Text))

Max Activating Token Index: 478

Text #3

Max Range: 0.0460. Min Range: -0.0460

Max Act: 0.0417. Min Act: -0.0003

Data Index: 474282 (C4 (Web Text))

Max Activating Token Index: 675

Text #4

Max Range: 0.0460. Min Range: -0.0460

Max Act: 0.0397. Min Act: -0.0003

Data Index: 273226 (C4 (Web Text))

Max Activating Token Index: 1003

Text #5

Max Range: 0.0460. Min Range: -0.0460

Max Act: 0.0410. Min Act: -0.0003

Data Index: 1091787 (C4 (Web Text))

Max Activating Token Index: 263

Text #6

Max Range: 0.0460. Min Range: -0.0460

Max Act: 0.0396. Min Act: -0.0004

Data Index: 322912 (C4 (Web Text))

Max Activating Token Index: 529

Text #7

Max Range: 0.0460. Min Range: -0.0460

Max Act: 0.0383. Min Act: -0.0003

Data Index: 239510 (C4 (Web Text))

Max Activating Token Index: 569

Text #8

Max Range: 0.0460. Min Range: -0.0460

Max Act: 0.0389. Min Act: -0.0003

Data Index: 1176444 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.0460. Min Range: -0.0460

Max Act: 0.0377. Min Act: -0.0003

Data Index: 1015432 (C4 (Web Text))

Max Activating Token Index: 218

Text #10

Max Range: 0.0460. Min Range: -0.0460

Max Act: 0.0384. Min Act: -0.0003

Data Index: 1115981 (C4 (Web Text))

Max Activating Token Index: 418

Text #11

Max Range: 0.0460. Min Range: -0.0460

Max Act: 0.0389. Min Act: -0.0003

Data Index: 16543 (C4 (Web Text))

Max Activating Token Index: 958

Text #12

Max Range: 0.0460. Min Range: -0.0460

Max Act: 0.0373. Min Act: -0.0003

Data Index: 952789 (C4 (Web Text))

Max Activating Token Index: 901

Text #13

Max Range: 0.0460. Min Range: -0.0460

Max Act: 0.0368. Min Act: -0.0003

Data Index: 309922 (C4 (Web Text))

Max Activating Token Index: 1010

Text #14

Max Range: 0.0460. Min Range: -0.0460

Max Act: 0.0373. Min Act: -0.0003

Data Index: 43427 (C4 (Web Text))

Max Activating Token Index: 859

Text #15

Max Range: 0.0460. Min Range: -0.0460

Max Act: 0.0366. Min Act: -0.0004

Data Index: 855767 (C4 (Web Text))

Max Activating Token Index: 315

Text #16

Max Range: 0.0460. Min Range: -0.0460

Max Act: 0.0359. Min Act: -0.0002

Data Index: 970192 (C4 (Web Text))

Max Activating Token Index: 939

Text #17

Max Range: 0.0460. Min Range: -0.0460

Max Act: 0.0363. Min Act: -0.0003

Data Index: 872049 (C4 (Web Text))

Max Activating Token Index: 817

Text #18

Max Range: 0.0460. Min Range: -0.0460

Max Act: 0.0362. Min Act: -0.0004

Data Index: 95660 (C4 (Web Text))

Max Activating Token Index: 186

Text #19

Max Range: 0.0460. Min Range: -0.0460

Max Act: 0.0377. Min Act: -0.0003

Data Index: 281097 (C4 (Web Text))

Max Activating Token Index: 230