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

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

Neuron 2604 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0371. Min Range: -0.0371

Max Act: 0.0359. Min Act: -0.0003

Data Index: 612160 (C4 (Web Text))

Max Activating Token Index: 736

Text #1

Max Range: 0.0371. Min Range: -0.0371

Max Act: 0.0359. Min Act: -0.0003

Data Index: 636545 (C4 (Web Text))

Max Activating Token Index: 64

Text #2

Max Range: 0.0371. Min Range: -0.0371

Max Act: 0.0365. Min Act: -0.0002

Data Index: 24720 (C4 (Web Text))

Max Activating Token Index: 472

Text #3

Max Range: 0.0371. Min Range: -0.0371

Max Act: 0.0371. Min Act: -0.0003

Data Index: 627292 (C4 (Web Text))

Max Activating Token Index: 44

Text #4

Max Range: 0.0371. Min Range: -0.0371

Max Act: 0.0356. Min Act: -0.0003

Data Index: 627162 (C4 (Web Text))

Max Activating Token Index: 273

Text #5

Max Range: 0.0371. Min Range: -0.0371

Max Act: 0.0342. Min Act: -0.0003

Data Index: 110511 (C4 (Web Text))

Max Activating Token Index: 45

Text #6

Max Range: 0.0371. Min Range: -0.0371

Max Act: 0.0355. Min Act: -0.0003

Data Index: 1260887 (C4 (Web Text))

Max Activating Token Index: 25

Text #7

Max Range: 0.0371. Min Range: -0.0371

Max Act: 0.0353. Min Act: -0.0003

Data Index: 1283016 (C4 (Web Text))

Max Activating Token Index: 488

Text #8

Max Range: 0.0371. Min Range: -0.0371

Max Act: 0.0342. Min Act: -0.0003

Data Index: 287397 (C4 (Web Text))

Max Activating Token Index: 54

Text #9

Max Range: 0.0371. Min Range: -0.0371

Max Act: 0.0350. Min Act: -0.0003

Data Index: 826350 (C4 (Web Text))

Max Activating Token Index: 338

Text #10

Max Range: 0.0371. Min Range: -0.0371

Max Act: 0.0339. Min Act: -0.0003

Data Index: 475970 (C4 (Web Text))

Max Activating Token Index: 50

Text #11

Max Range: 0.0371. Min Range: -0.0371

Max Act: 0.0319. Min Act: -0.0003

Data Index: 1236159 (C4 (Web Text))

Max Activating Token Index: 540

Text #12

Max Range: 0.0371. Min Range: -0.0371

Max Act: 0.0324. Min Act: -0.0003

Data Index: 1096029 (C4 (Web Text))

Max Activating Token Index: 513

Text #13

Max Range: 0.0371. Min Range: -0.0371

Max Act: 0.0325. Min Act: -0.0003

Data Index: 347851 (C4 (Web Text))

Max Activating Token Index: 344

Text #14

Max Range: 0.0371. Min Range: -0.0371

Max Act: 0.0335. Min Act: -0.0003

Data Index: 1065136 (C4 (Web Text))

Max Activating Token Index: 460

Text #15

Max Range: 0.0371. Min Range: -0.0371

Max Act: 0.0322. Min Act: -0.0002

Data Index: 946291 (C4 (Web Text))

Max Activating Token Index: 25

Text #16

Max Range: 0.0371. Min Range: -0.0371

Max Act: 0.0325. Min Act: -0.0003

Data Index: 683139 (C4 (Web Text))

Max Activating Token Index: 569

Text #17

Max Range: 0.0371. Min Range: -0.0371

Max Act: 0.0304. Min Act: -0.0003

Data Index: 619896 (C4 (Web Text))

Max Activating Token Index: 263

Text #18

Max Range: 0.0371. Min Range: -0.0371

Max Act: 0.0322. Min Act: -0.0003

Data Index: 804673 (C4 (Web Text))

Max Activating Token Index: 264

Text #19

Max Range: 0.0371. Min Range: -0.0371

Max Act: 0.0316. Min Act: -0.0003

Data Index: 1115771 (C4 (Web Text))

Max Activating Token Index: 80