Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 485 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.0216. Min Range: -0.0216

Max Act: 0.0216. Min Act: -0.0002

Data Index: 52021 (C4 (Web Text))

Max Activating Token Index: 81

Text #1

Max Range: 0.0216. Min Range: -0.0216

Max Act: 0.0215. Min Act: -0.0001

Data Index: 1191141 (C4 (Web Text))

Max Activating Token Index: 228

Text #2

Max Range: 0.0216. Min Range: -0.0216

Max Act: 0.0211. Min Act: -0.0001

Data Index: 704189 (C4 (Web Text))

Max Activating Token Index: 122

Text #3

Max Range: 0.0216. Min Range: -0.0216

Max Act: 0.0210. Min Act: -0.0001

Data Index: 825741 (C4 (Web Text))

Max Activating Token Index: 176

Text #4

Max Range: 0.0216. Min Range: -0.0216

Max Act: 0.0210. Min Act: -0.0001

Data Index: 1328743 (C4 (Web Text))

Max Activating Token Index: 577

Text #5

Max Range: 0.0216. Min Range: -0.0216

Max Act: 0.0213. Min Act: -0.0001

Data Index: 1140948 (C4 (Web Text))

Max Activating Token Index: 688

Text #6

Max Range: 0.0216. Min Range: -0.0216

Max Act: 0.0205. Min Act: -0.0001

Data Index: 697725 (C4 (Web Text))

Max Activating Token Index: 53

Text #7

Max Range: 0.0216. Min Range: -0.0216

Max Act: 0.0204. Min Act: -0.0001

Data Index: 1064828 (C4 (Web Text))

Max Activating Token Index: 218

Text #8

Max Range: 0.0216. Min Range: -0.0216

Max Act: 0.0203. Min Act: -0.0001

Data Index: 314254 (C4 (Web Text))

Max Activating Token Index: 967

Text #9

Max Range: 0.0216. Min Range: -0.0216

Max Act: 0.0205. Min Act: -0.0001

Data Index: 476734 (C4 (Web Text))

Max Activating Token Index: 505

Text #10

Max Range: 0.0216. Min Range: -0.0216

Max Act: 0.0203. Min Act: -0.0001

Data Index: 364175 (C4 (Web Text))

Max Activating Token Index: 181

Text #11

Max Range: 0.0216. Min Range: -0.0216

Max Act: 0.0204. Min Act: -0.0001

Data Index: 382411 (C4 (Web Text))

Max Activating Token Index: 474

Text #12

Max Range: 0.0216. Min Range: -0.0216

Max Act: 0.0205. Min Act: -0.0001

Data Index: 1009680 (C4 (Web Text))

Max Activating Token Index: 925

Text #13

Max Range: 0.0216. Min Range: -0.0216

Max Act: 0.0204. Min Act: -0.0001

Data Index: 1224735 (C4 (Web Text))

Max Activating Token Index: 147

Text #14

Max Range: 0.0216. Min Range: -0.0216

Max Act: 0.0202. Min Act: -0.0002

Data Index: 545652 (C4 (Web Text))

Max Activating Token Index: 814

Text #15

Max Range: 0.0216. Min Range: -0.0216

Max Act: 0.0205. Min Act: -0.0001

Data Index: 1510227 (Python Code)

Max Activating Token Index: 138

Text #16

Max Range: 0.0216. Min Range: -0.0216

Max Act: 0.0207. Min Act: -0.0001

Data Index: 1184639 (C4 (Web Text))

Max Activating Token Index: 191

Text #17

Max Range: 0.0216. Min Range: -0.0216

Max Act: 0.0205. Min Act: -0.0001

Data Index: 1225946 (C4 (Web Text))

Max Activating Token Index: 116

Text #18

Max Range: 0.0216. Min Range: -0.0216

Max Act: 0.0207. Min Act: -0.0001

Data Index: 1337659 (C4 (Web Text))

Max Activating Token Index: 21

Text #19

Max Range: 0.0216. Min Range: -0.0216

Max Act: 0.0208. Min Act: -0.0001

Data Index: 322939 (C4 (Web Text))

Max Activating Token Index: 909