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

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

Neuron 1634 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0342. Min Act: -0.0005

Data Index: 830811 (C4 (Web Text))

Max Activating Token Index: 949

Text #1

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0329. Min Act: -0.0004

Data Index: 529053 (C4 (Web Text))

Max Activating Token Index: 347

Text #2

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0321. Min Act: -0.0005

Data Index: 986727 (C4 (Web Text))

Max Activating Token Index: 668

Text #3

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0316. Min Act: -0.0004

Data Index: 817174 (C4 (Web Text))

Max Activating Token Index: 262

Text #4

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0280. Min Act: -0.0004

Data Index: 921241 (C4 (Web Text))

Max Activating Token Index: 212

Text #5

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0272. Min Act: -0.0005

Data Index: 1018354 (C4 (Web Text))

Max Activating Token Index: 930

Text #6

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0271. Min Act: -0.0003

Data Index: 1341311 (C4 (Web Text))

Max Activating Token Index: 364

Text #7

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0275. Min Act: -0.0005

Data Index: 1015297 (C4 (Web Text))

Max Activating Token Index: 924

Text #8

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0271. Min Act: -0.0004

Data Index: 419595 (C4 (Web Text))

Max Activating Token Index: 228

Text #9

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0269. Min Act: -0.0004

Data Index: 951519 (C4 (Web Text))

Max Activating Token Index: 229

Text #10

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0263. Min Act: -0.0004

Data Index: 1319289 (C4 (Web Text))

Max Activating Token Index: 248

Text #11

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0259. Min Act: -0.0004

Data Index: 369523 (C4 (Web Text))

Max Activating Token Index: 481

Text #12

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0254. Min Act: -0.0005

Data Index: 1115924 (C4 (Web Text))

Max Activating Token Index: 887

Text #13

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0258. Min Act: -0.0004

Data Index: 1278409 (C4 (Web Text))

Max Activating Token Index: 148

Text #14

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0256. Min Act: -0.0004

Data Index: 748801 (C4 (Web Text))

Max Activating Token Index: 898

Text #15

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0250. Min Act: -0.0005

Data Index: 1131520 (C4 (Web Text))

Max Activating Token Index: 250

Text #16

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0251. Min Act: -0.0004

Data Index: 142833 (C4 (Web Text))

Max Activating Token Index: 175

Text #17

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0250. Min Act: -0.0005

Data Index: 705348 (C4 (Web Text))

Max Activating Token Index: 179

Text #18

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0244. Min Act: -0.0005

Data Index: 1315177 (C4 (Web Text))

Max Activating Token Index: 616

Text #19

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0248. Min Act: -0.0004

Data Index: 1358531 (C4 (Web Text))

Max Activating Token Index: 452