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

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

Neuron 2873 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: 0.0485. Min Range: -0.0485

Max Act: 0.0485. Min Act: -0.0002

Data Index: 1113034 (C4 (Web Text))

Max Activating Token Index: 316

Text #1

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0373. Min Act: -0.0002

Data Index: 1281763 (C4 (Web Text))

Max Activating Token Index: 620

Text #2

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0384. Min Act: -0.0002

Data Index: 1052577 (C4 (Web Text))

Max Activating Token Index: 584

Text #3

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0365. Min Act: -0.0002

Data Index: 567178 (C4 (Web Text))

Max Activating Token Index: 846

Text #4

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0384. Min Act: -0.0002

Data Index: 780770 (C4 (Web Text))

Max Activating Token Index: 783

Text #5

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0382. Min Act: -0.0003

Data Index: 62387 (C4 (Web Text))

Max Activating Token Index: 897

Text #6

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0335. Min Act: -0.0002

Data Index: 320011 (C4 (Web Text))

Max Activating Token Index: 600

Text #7

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0348. Min Act: -0.0003

Data Index: 735044 (C4 (Web Text))

Max Activating Token Index: 653

Text #8

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0346. Min Act: -0.0002

Data Index: 526196 (C4 (Web Text))

Max Activating Token Index: 851

Text #9

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0334. Min Act: -0.0002

Data Index: 424780 (C4 (Web Text))

Max Activating Token Index: 429

Text #10

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0308. Min Act: -0.0002

Data Index: 1232301 (C4 (Web Text))

Max Activating Token Index: 429

Text #11

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0319. Min Act: -0.0002

Data Index: 973114 (C4 (Web Text))

Max Activating Token Index: 513

Text #12

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0305. Min Act: -0.0002

Data Index: 681409 (C4 (Web Text))

Max Activating Token Index: 202

Text #13

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0297. Min Act: -0.0003

Data Index: 1130230 (C4 (Web Text))

Max Activating Token Index: 580

Text #14

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0293. Min Act: -0.0003

Data Index: 493915 (C4 (Web Text))

Max Activating Token Index: 119

Text #15

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0293. Min Act: -0.0002

Data Index: 1196965 (C4 (Web Text))

Max Activating Token Index: 726

Text #16

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0291. Min Act: -0.0003

Data Index: 121338 (C4 (Web Text))

Max Activating Token Index: 500

Text #17

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0287. Min Act: -0.0003

Data Index: 739422 (C4 (Web Text))

Max Activating Token Index: 846

Text #18

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0280. Min Act: -0.0002

Data Index: 392742 (C4 (Web Text))

Max Activating Token Index: 836

Text #19

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0283. Min Act: -0.0003

Data Index: 498059 (C4 (Web Text))

Max Activating Token Index: 653