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

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

Neuron 1143 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: 0.0399. Min Range: -0.0399

Max Act: 0.0399. Min Act: -0.0002

Data Index: 994966 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.0399. Min Range: -0.0399

Max Act: 0.0306. Min Act: -0.0001

Data Index: 66737 (C4 (Web Text))

Max Activating Token Index: 770

Text #2

Max Range: 0.0399. Min Range: -0.0399

Max Act: 0.0284. Min Act: -0.0002

Data Index: 447349 (C4 (Web Text))

Max Activating Token Index: 168

Text #3

Max Range: 0.0399. Min Range: -0.0399

Max Act: 0.0311. Min Act: -0.0002

Data Index: 206412 (C4 (Web Text))

Max Activating Token Index: 367

Text #4

Max Range: 0.0399. Min Range: -0.0399

Max Act: 0.0256. Min Act: -0.0002

Data Index: 44870 (C4 (Web Text))

Max Activating Token Index: 765

Text #5

Max Range: 0.0399. Min Range: -0.0399

Max Act: 0.0286. Min Act: -0.0002

Data Index: 1112562 (C4 (Web Text))

Max Activating Token Index: 33

Text #6

Max Range: 0.0399. Min Range: -0.0399

Max Act: 0.0280. Min Act: -0.0002

Data Index: 814719 (C4 (Web Text))

Max Activating Token Index: 877

Text #7

Max Range: 0.0399. Min Range: -0.0399

Max Act: 0.0272. Min Act: -0.0002

Data Index: 892401 (C4 (Web Text))

Max Activating Token Index: 466

Text #8

Max Range: 0.0399. Min Range: -0.0399

Max Act: 0.0279. Min Act: -0.0003

Data Index: 1550910 (Python Code)

Max Activating Token Index: 696

Text #9

Max Range: 0.0399. Min Range: -0.0399

Max Act: 0.0248. Min Act: -0.0001

Data Index: 225224 (C4 (Web Text))

Max Activating Token Index: 651

Text #10

Max Range: 0.0399. Min Range: -0.0399

Max Act: 0.0266. Min Act: 0.0000

Data Index: 1214000 (C4 (Web Text))

Max Activating Token Index: 553

Text #11

Max Range: 0.0399. Min Range: -0.0399

Max Act: 0.0268. Min Act: -0.0002

Data Index: 582953 (C4 (Web Text))

Max Activating Token Index: 532

Text #12

Max Range: 0.0399. Min Range: -0.0399

Max Act: 0.0259. Min Act: -0.0003

Data Index: 1614248 (Python Code)

Max Activating Token Index: 789

Text #13

Max Range: 0.0399. Min Range: -0.0399

Max Act: 0.0240. Min Act: -0.0002

Data Index: 327266 (C4 (Web Text))

Max Activating Token Index: 240

Text #14

Max Range: 0.0399. Min Range: -0.0399

Max Act: 0.0231. Min Act: -0.0002

Data Index: 985894 (C4 (Web Text))

Max Activating Token Index: 949

Text #15

Max Range: 0.0399. Min Range: -0.0399

Max Act: 0.0242. Min Act: -0.0001

Data Index: 99131 (C4 (Web Text))

Max Activating Token Index: 24

Text #16

Max Range: 0.0399. Min Range: -0.0399

Max Act: 0.0251. Min Act: -0.0000

Data Index: 1223240 (C4 (Web Text))

Max Activating Token Index: 837

Text #17

Max Range: 0.0399. Min Range: -0.0399

Max Act: 0.0237. Min Act: -0.0002

Data Index: 943196 (C4 (Web Text))

Max Activating Token Index: 213

Text #18

Max Range: 0.0399. Min Range: -0.0399

Max Act: 0.0229. Min Act: -0.0001

Data Index: 290035 (C4 (Web Text))

Max Activating Token Index: 80

Text #19

Max Range: 0.0399. Min Range: -0.0399

Max Act: 0.0251. Min Act: -0.0002

Data Index: 167664 (C4 (Web Text))

Max Activating Token Index: 416