Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2859 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0269. Min Range: -0.0269

Max Act: 0.0269. Min Act: -0.0003

Data Index: 672515 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.0269. Min Range: -0.0269

Max Act: 0.0224. Min Act: -0.0003

Data Index: 386166 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.0269. Min Range: -0.0269

Max Act: 0.0215. Min Act: -0.0003

Data Index: 1288400 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.0269. Min Range: -0.0269

Max Act: 0.0206. Min Act: -0.0003

Data Index: 1238875 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.0269. Min Range: -0.0269

Max Act: 0.0190. Min Act: -0.0003

Data Index: 362608 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.0269. Min Range: -0.0269

Max Act: 0.0202. Min Act: -0.0003

Data Index: 1065885 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.0269. Min Range: -0.0269

Max Act: 0.0195. Min Act: -0.0003

Data Index: 458535 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.0269. Min Range: -0.0269

Max Act: 0.0187. Min Act: -0.0003

Data Index: 789439 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.0269. Min Range: -0.0269

Max Act: 0.0178. Min Act: -0.0003

Data Index: 1221265 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.0269. Min Range: -0.0269

Max Act: 0.0172. Min Act: -0.0003

Data Index: 118378 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.0269. Min Range: -0.0269

Max Act: 0.0162. Min Act: -0.0003

Data Index: 347436 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.0269. Min Range: -0.0269

Max Act: 0.0162. Min Act: -0.0003

Data Index: 1228428 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 0.0269. Min Range: -0.0269

Max Act: 0.0165. Min Act: -0.0003

Data Index: 1226527 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.0269. Min Range: -0.0269

Max Act: 0.0161. Min Act: -0.0003

Data Index: 492890 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 0.0269. Min Range: -0.0269

Max Act: 0.0174. Min Act: -0.0003

Data Index: 731286 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 0.0269. Min Range: -0.0269

Max Act: 0.0161. Min Act: -0.0003

Data Index: 1139667 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 0.0269. Min Range: -0.0269

Max Act: 0.0163. Min Act: -0.0003

Data Index: 221426 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 0.0269. Min Range: -0.0269

Max Act: 0.0161. Min Act: -0.0003

Data Index: 324609 (C4 (Web Text))

Max Activating Token Index: 662

Text #18

Max Range: 0.0269. Min Range: -0.0269

Max Act: 0.0143. Min Act: -0.0003

Data Index: 153168 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 0.0269. Min Range: -0.0269

Max Act: 0.0156. Min Act: -0.0003

Data Index: 495850 (C4 (Web Text))

Max Activating Token Index: 1023