Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1259 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0256. Min Range: -0.0256

Max Act: 0.0256. Min Act: -0.0003

Data Index: 621267 (C4 (Web Text))

Max Activating Token Index: 440

Text #1

Max Range: 0.0256. Min Range: -0.0256

Max Act: 0.0249. Min Act: -0.0003

Data Index: 361508 (C4 (Web Text))

Max Activating Token Index: 959

Text #2

Max Range: 0.0256. Min Range: -0.0256

Max Act: 0.0255. Min Act: -0.0003

Data Index: 541354 (C4 (Web Text))

Max Activating Token Index: 952

Text #3

Max Range: 0.0256. Min Range: -0.0256

Max Act: 0.0246. Min Act: -0.0003

Data Index: 1022511 (C4 (Web Text))

Max Activating Token Index: 640

Text #4

Max Range: 0.0256. Min Range: -0.0256

Max Act: 0.0233. Min Act: -0.0003

Data Index: 1258813 (C4 (Web Text))

Max Activating Token Index: 298

Text #5

Max Range: 0.0256. Min Range: -0.0256

Max Act: 0.0249. Min Act: -0.0003

Data Index: 1091088 (C4 (Web Text))

Max Activating Token Index: 110

Text #6

Max Range: 0.0256. Min Range: -0.0256

Max Act: 0.0247. Min Act: -0.0003

Data Index: 1094245 (C4 (Web Text))

Max Activating Token Index: 262

Text #7

Max Range: 0.0256. Min Range: -0.0256

Max Act: 0.0239. Min Act: -0.0003

Data Index: 730285 (C4 (Web Text))

Max Activating Token Index: 51

Text #8

Max Range: 0.0256. Min Range: -0.0256

Max Act: 0.0237. Min Act: -0.0003

Data Index: 1080744 (C4 (Web Text))

Max Activating Token Index: 121

Text #9

Max Range: 0.0256. Min Range: -0.0256

Max Act: 0.0238. Min Act: -0.0003

Data Index: 673982 (C4 (Web Text))

Max Activating Token Index: 159

Text #10

Max Range: 0.0256. Min Range: -0.0256

Max Act: 0.0230. Min Act: -0.0003

Data Index: 1465772 (Python Code)

Max Activating Token Index: 834

Text #11

Max Range: 0.0256. Min Range: -0.0256

Max Act: 0.0231. Min Act: -0.0003

Data Index: 861155 (C4 (Web Text))

Max Activating Token Index: 204

Text #12

Max Range: 0.0256. Min Range: -0.0256

Max Act: 0.0224. Min Act: -0.0003

Data Index: 647548 (C4 (Web Text))

Max Activating Token Index: 164

Text #13

Max Range: 0.0256. Min Range: -0.0256

Max Act: 0.0229. Min Act: -0.0003

Data Index: 1055891 (C4 (Web Text))

Max Activating Token Index: 546

Text #14

Max Range: 0.0256. Min Range: -0.0256

Max Act: 0.0224. Min Act: -0.0003

Data Index: 281967 (C4 (Web Text))

Max Activating Token Index: 292

Text #15

Max Range: 0.0256. Min Range: -0.0256

Max Act: 0.0228. Min Act: -0.0003

Data Index: 1397284 (Python Code)

Max Activating Token Index: 155

Text #16

Max Range: 0.0256. Min Range: -0.0256

Max Act: 0.0231. Min Act: -0.0003

Data Index: 404465 (C4 (Web Text))

Max Activating Token Index: 39

Text #17

Max Range: 0.0256. Min Range: -0.0256

Max Act: 0.0227. Min Act: -0.0003

Data Index: 348898 (C4 (Web Text))

Max Activating Token Index: 960

Text #18

Max Range: 0.0256. Min Range: -0.0256

Max Act: 0.0230. Min Act: -0.0003

Data Index: 88268 (C4 (Web Text))

Max Activating Token Index: 949

Text #19

Max Range: 0.0256. Min Range: -0.0256

Max Act: 0.0221. Min Act: -0.0003

Data Index: 417537 (C4 (Web Text))

Max Activating Token Index: 276