Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 554 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0388. Min Range: -0.0388

Max Act: 0.0388. Min Act: -0.0002

Data Index: 1209463 (C4 (Web Text))

Max Activating Token Index: 493

Text #1

Max Range: 0.0388. Min Range: -0.0388

Max Act: 0.0379. Min Act: -0.0002

Data Index: 1023075 (C4 (Web Text))

Max Activating Token Index: 296

Text #2

Max Range: 0.0388. Min Range: -0.0388

Max Act: 0.0374. Min Act: -0.0002

Data Index: 876540 (C4 (Web Text))

Max Activating Token Index: 325

Text #3

Max Range: 0.0388. Min Range: -0.0388

Max Act: 0.0373. Min Act: -0.0002

Data Index: 603621 (C4 (Web Text))

Max Activating Token Index: 260

Text #4

Max Range: 0.0388. Min Range: -0.0388

Max Act: 0.0364. Min Act: -0.0002

Data Index: 318817 (C4 (Web Text))

Max Activating Token Index: 878

Text #5

Max Range: 0.0388. Min Range: -0.0388

Max Act: 0.0369. Min Act: -0.0002

Data Index: 689507 (C4 (Web Text))

Max Activating Token Index: 204

Text #6

Max Range: 0.0388. Min Range: -0.0388

Max Act: 0.0367. Min Act: -0.0002

Data Index: 488191 (C4 (Web Text))

Max Activating Token Index: 341

Text #7

Max Range: 0.0388. Min Range: -0.0388

Max Act: 0.0367. Min Act: -0.0002

Data Index: 1150449 (C4 (Web Text))

Max Activating Token Index: 856

Text #8

Max Range: 0.0388. Min Range: -0.0388

Max Act: 0.0365. Min Act: -0.0002

Data Index: 1079047 (C4 (Web Text))

Max Activating Token Index: 747

Text #9

Max Range: 0.0388. Min Range: -0.0388

Max Act: 0.0365. Min Act: -0.0002

Data Index: 890308 (C4 (Web Text))

Max Activating Token Index: 824

Text #10

Max Range: 0.0388. Min Range: -0.0388

Max Act: 0.0364. Min Act: -0.0002

Data Index: 675815 (C4 (Web Text))

Max Activating Token Index: 890

Text #11

Max Range: 0.0388. Min Range: -0.0388

Max Act: 0.0363. Min Act: -0.0002

Data Index: 105726 (C4 (Web Text))

Max Activating Token Index: 908

Text #12

Max Range: 0.0388. Min Range: -0.0388

Max Act: 0.0361. Min Act: -0.0002

Data Index: 750150 (C4 (Web Text))

Max Activating Token Index: 972

Text #13

Max Range: 0.0388. Min Range: -0.0388

Max Act: 0.0360. Min Act: -0.0002

Data Index: 1039900 (C4 (Web Text))

Max Activating Token Index: 605

Text #14

Max Range: 0.0388. Min Range: -0.0388

Max Act: 0.0359. Min Act: -0.0002

Data Index: 207954 (C4 (Web Text))

Max Activating Token Index: 344

Text #15

Max Range: 0.0388. Min Range: -0.0388

Max Act: 0.0366. Min Act: -0.0002

Data Index: 907434 (C4 (Web Text))

Max Activating Token Index: 163

Text #16

Max Range: 0.0388. Min Range: -0.0388

Max Act: 0.0358. Min Act: -0.0002

Data Index: 896507 (C4 (Web Text))

Max Activating Token Index: 431

Text #17

Max Range: 0.0388. Min Range: -0.0388

Max Act: 0.0350. Min Act: -0.0002

Data Index: 325165 (C4 (Web Text))

Max Activating Token Index: 539

Text #18

Max Range: 0.0388. Min Range: -0.0388

Max Act: 0.0356. Min Act: -0.0002

Data Index: 70843 (C4 (Web Text))

Max Activating Token Index: 548

Text #19

Max Range: 0.0388. Min Range: -0.0388

Max Act: 0.0356. Min Act: -0.0002

Data Index: 940586 (C4 (Web Text))

Max Activating Token Index: 494