Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 506 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0329. Min Act: -0.0003

Data Index: 827898 (C4 (Web Text))

Max Activating Token Index: 19

Text #1

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0328. Min Act: -0.0003

Data Index: 828616 (C4 (Web Text))

Max Activating Token Index: 104

Text #2

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0309. Min Act: -0.0003

Data Index: 45840 (C4 (Web Text))

Max Activating Token Index: 146

Text #3

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0316. Min Act: -0.0003

Data Index: 1018786 (C4 (Web Text))

Max Activating Token Index: 108

Text #4

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0302. Min Act: -0.0003

Data Index: 845831 (C4 (Web Text))

Max Activating Token Index: 873

Text #5

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0293. Min Act: -0.0003

Data Index: 927464 (C4 (Web Text))

Max Activating Token Index: 317

Text #6

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0296. Min Act: -0.0003

Data Index: 1162720 (C4 (Web Text))

Max Activating Token Index: 849

Text #7

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0295. Min Act: -0.0003

Data Index: 386085 (C4 (Web Text))

Max Activating Token Index: 777

Text #8

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0280. Min Act: -0.0003

Data Index: 35677 (C4 (Web Text))

Max Activating Token Index: 165

Text #9

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0280. Min Act: -0.0003

Data Index: 1181947 (C4 (Web Text))

Max Activating Token Index: 113

Text #10

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0283. Min Act: -0.0003

Data Index: 576259 (C4 (Web Text))

Max Activating Token Index: 29

Text #11

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0277. Min Act: -0.0003

Data Index: 140089 (C4 (Web Text))

Max Activating Token Index: 470

Text #12

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0268. Min Act: -0.0003

Data Index: 608135 (C4 (Web Text))

Max Activating Token Index: 132

Text #13

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0273. Min Act: -0.0003

Data Index: 574763 (C4 (Web Text))

Max Activating Token Index: 212

Text #14

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0271. Min Act: -0.0002

Data Index: 912961 (C4 (Web Text))

Max Activating Token Index: 667

Text #15

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0269. Min Act: -0.0003

Data Index: 518468 (C4 (Web Text))

Max Activating Token Index: 234

Text #16

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0269. Min Act: -0.0003

Data Index: 1304680 (C4 (Web Text))

Max Activating Token Index: 215

Text #17

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0266. Min Act: -0.0003

Data Index: 995346 (C4 (Web Text))

Max Activating Token Index: 103

Text #18

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0263. Min Act: -0.0003

Data Index: 1107267 (C4 (Web Text))

Max Activating Token Index: 468

Text #19

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0268. Min Act: -0.0003

Data Index: 1487608 (Python Code)

Max Activating Token Index: 526