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

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

Neuron 1745 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: 0.0368. Min Range: -0.0368

Max Act: 0.0368. Min Act: -0.0002

Data Index: 722069 (C4 (Web Text))

Max Activating Token Index: 763

Text #1

Max Range: 0.0368. Min Range: -0.0368

Max Act: 0.0332. Min Act: -0.0003

Data Index: 625508 (C4 (Web Text))

Max Activating Token Index: 42

Text #2

Max Range: 0.0368. Min Range: -0.0368

Max Act: 0.0322. Min Act: -0.0003

Data Index: 374702 (C4 (Web Text))

Max Activating Token Index: 60

Text #3

Max Range: 0.0368. Min Range: -0.0368

Max Act: 0.0317. Min Act: -0.0002

Data Index: 489924 (C4 (Web Text))

Max Activating Token Index: 666

Text #4

Max Range: 0.0368. Min Range: -0.0368

Max Act: 0.0305. Min Act: -0.0003

Data Index: 611219 (C4 (Web Text))

Max Activating Token Index: 498

Text #5

Max Range: 0.0368. Min Range: -0.0368

Max Act: 0.0292. Min Act: -0.0003

Data Index: 748431 (C4 (Web Text))

Max Activating Token Index: 447

Text #6

Max Range: 0.0368. Min Range: -0.0368

Max Act: 0.0288. Min Act: -0.0003

Data Index: 307168 (C4 (Web Text))

Max Activating Token Index: 271

Text #7

Max Range: 0.0368. Min Range: -0.0368

Max Act: 0.0280. Min Act: -0.0002

Data Index: 990210 (C4 (Web Text))

Max Activating Token Index: 13

Text #8

Max Range: 0.0368. Min Range: -0.0368

Max Act: 0.0280. Min Act: -0.0003

Data Index: 462887 (C4 (Web Text))

Max Activating Token Index: 1003

Text #9

Max Range: 0.0368. Min Range: -0.0368

Max Act: 0.0264. Min Act: -0.0003

Data Index: 737641 (C4 (Web Text))

Max Activating Token Index: 182

Text #10

Max Range: 0.0368. Min Range: -0.0368

Max Act: 0.0267. Min Act: -0.0002

Data Index: 97536 (C4 (Web Text))

Max Activating Token Index: 765

Text #11

Max Range: 0.0368. Min Range: -0.0368

Max Act: 0.0266. Min Act: -0.0003

Data Index: 951507 (C4 (Web Text))

Max Activating Token Index: 371

Text #12

Max Range: 0.0368. Min Range: -0.0368

Max Act: 0.0249. Min Act: -0.0002

Data Index: 904826 (C4 (Web Text))

Max Activating Token Index: 507

Text #13

Max Range: 0.0368. Min Range: -0.0368

Max Act: 0.0240. Min Act: -0.0003

Data Index: 1166022 (C4 (Web Text))

Max Activating Token Index: 16

Text #14

Max Range: 0.0368. Min Range: -0.0368

Max Act: 0.0236. Min Act: -0.0003

Data Index: 678335 (C4 (Web Text))

Max Activating Token Index: 105

Text #15

Max Range: 0.0368. Min Range: -0.0368

Max Act: 0.0240. Min Act: -0.0002

Data Index: 1212778 (C4 (Web Text))

Max Activating Token Index: 593

Text #16

Max Range: 0.0368. Min Range: -0.0368

Max Act: 0.0239. Min Act: -0.0002

Data Index: 1249416 (C4 (Web Text))

Max Activating Token Index: 75

Text #17

Max Range: 0.0368. Min Range: -0.0368

Max Act: 0.0236. Min Act: -0.0003

Data Index: 300315 (C4 (Web Text))

Max Activating Token Index: 786

Text #18

Max Range: 0.0368. Min Range: -0.0368

Max Act: 0.0233. Min Act: -0.0003

Data Index: 1275783 (C4 (Web Text))

Max Activating Token Index: 72

Text #19

Max Range: 0.0368. Min Range: -0.0368

Max Act: 0.0232. Min Act: -0.0003

Data Index: 276910 (C4 (Web Text))

Max Activating Token Index: 332