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

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

Neuron 2412 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3496. Min Range: -0.3496

Max Act: 0.3496. Min Act: -0.0001

Data Index: 533424 (C4 (Web Text))

Max Activating Token Index: 775

Text #1

Max Range: 0.3496. Min Range: -0.3496

Max Act: 0.3172. Min Act: -0.0001

Data Index: 836816 (C4 (Web Text))

Max Activating Token Index: 48

Text #2

Max Range: 0.3496. Min Range: -0.3496

Max Act: 0.3222. Min Act: -0.0001

Data Index: 590314 (C4 (Web Text))

Max Activating Token Index: 874

Text #3

Max Range: 0.3496. Min Range: -0.3496

Max Act: 0.2809. Min Act: -0.0001

Data Index: 184291 (C4 (Web Text))

Max Activating Token Index: 979

Text #4

Max Range: 0.3496. Min Range: -0.3496

Max Act: 0.2692. Min Act: -0.0000

Data Index: 829952 (C4 (Web Text))

Max Activating Token Index: 32

Text #5

Max Range: 0.3496. Min Range: -0.3496

Max Act: 0.2661. Min Act: -0.0001

Data Index: 126800 (C4 (Web Text))

Max Activating Token Index: 908

Text #6

Max Range: 0.3496. Min Range: -0.3496

Max Act: 0.2535. Min Act: -0.0001

Data Index: 50375 (C4 (Web Text))

Max Activating Token Index: 49

Text #7

Max Range: 0.3496. Min Range: -0.3496

Max Act: 0.2523. Min Act: -0.0001

Data Index: 644594 (C4 (Web Text))

Max Activating Token Index: 911

Text #8

Max Range: 0.3496. Min Range: -0.3496

Max Act: 0.2524. Min Act: -0.0001

Data Index: 1152741 (C4 (Web Text))

Max Activating Token Index: 218

Text #9

Max Range: 0.3496. Min Range: -0.3496

Max Act: 0.2508. Min Act: -0.0001

Data Index: 562226 (C4 (Web Text))

Max Activating Token Index: 462

Text #10

Max Range: 0.3496. Min Range: -0.3496

Max Act: 0.2319. Min Act: -0.0001

Data Index: 602532 (C4 (Web Text))

Max Activating Token Index: 770

Text #11

Max Range: 0.3496. Min Range: -0.3496

Max Act: 0.2466. Min Act: -0.0001

Data Index: 723 (C4 (Web Text))

Max Activating Token Index: 207

Text #12

Max Range: 0.3496. Min Range: -0.3496

Max Act: 0.2422. Min Act: -0.0001

Data Index: 1176106 (C4 (Web Text))

Max Activating Token Index: 1016

Text #13

Max Range: 0.3496. Min Range: -0.3496

Max Act: 0.2416. Min Act: -0.0001

Data Index: 714940 (C4 (Web Text))

Max Activating Token Index: 407

Text #14

Max Range: 0.3496. Min Range: -0.3496

Max Act: 0.2301. Min Act: -0.0001

Data Index: 1116777 (C4 (Web Text))

Max Activating Token Index: 569

Text #15

Max Range: 0.3496. Min Range: -0.3496

Max Act: 0.2366. Min Act: -0.0001

Data Index: 1047968 (C4 (Web Text))

Max Activating Token Index: 354

Text #16

Max Range: 0.3496. Min Range: -0.3496

Max Act: 0.2369. Min Act: -0.0001

Data Index: 880137 (C4 (Web Text))

Max Activating Token Index: 626

Text #17

Max Range: 0.3496. Min Range: -0.3496

Max Act: 0.2414. Min Act: -0.0001

Data Index: 235687 (C4 (Web Text))

Max Activating Token Index: 318

Text #18

Max Range: 0.3496. Min Range: -0.3496

Max Act: 0.2266. Min Act: -0.0001

Data Index: 632440 (C4 (Web Text))

Max Activating Token Index: 446

Text #19

Max Range: 0.3496. Min Range: -0.3496

Max Act: 0.2345. Min Act: -0.0001

Data Index: 498366 (C4 (Web Text))

Max Activating Token Index: 705