Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 768 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0187. Min Range: -0.0187

Max Act: 0.0187. Min Act: -0.0003

Data Index: 792941 (C4 (Web Text))

Max Activating Token Index: 180

Text #1

Max Range: 0.0187. Min Range: -0.0187

Max Act: 0.0186. Min Act: -0.0003

Data Index: 479188 (C4 (Web Text))

Max Activating Token Index: 648

Text #2

Max Range: 0.0187. Min Range: -0.0187

Max Act: 0.0184. Min Act: -0.0003

Data Index: 1171208 (C4 (Web Text))

Max Activating Token Index: 801

Text #3

Max Range: 0.0187. Min Range: -0.0187

Max Act: 0.0179. Min Act: -0.0003

Data Index: 425343 (C4 (Web Text))

Max Activating Token Index: 261

Text #4

Max Range: 0.0187. Min Range: -0.0187

Max Act: 0.0161. Min Act: -0.0003

Data Index: 1241938 (C4 (Web Text))

Max Activating Token Index: 51

Text #5

Max Range: 0.0187. Min Range: -0.0187

Max Act: 0.0158. Min Act: -0.0003

Data Index: 583183 (C4 (Web Text))

Max Activating Token Index: 516

Text #6

Max Range: 0.0187. Min Range: -0.0187

Max Act: 0.0156. Min Act: -0.0003

Data Index: 143743 (C4 (Web Text))

Max Activating Token Index: 245

Text #7

Max Range: 0.0187. Min Range: -0.0187

Max Act: 0.0162. Min Act: -0.0003

Data Index: 1118232 (C4 (Web Text))

Max Activating Token Index: 600

Text #8

Max Range: 0.0187. Min Range: -0.0187

Max Act: 0.0163. Min Act: -0.0003

Data Index: 1338351 (C4 (Web Text))

Max Activating Token Index: 165

Text #9

Max Range: 0.0187. Min Range: -0.0187

Max Act: 0.0159. Min Act: -0.0003

Data Index: 168668 (C4 (Web Text))

Max Activating Token Index: 272

Text #10

Max Range: 0.0187. Min Range: -0.0187

Max Act: 0.0149. Min Act: -0.0003

Data Index: 341346 (C4 (Web Text))

Max Activating Token Index: 46

Text #11

Max Range: 0.0187. Min Range: -0.0187

Max Act: 0.0151. Min Act: -0.0003

Data Index: 937448 (C4 (Web Text))

Max Activating Token Index: 442

Text #12

Max Range: 0.0187. Min Range: -0.0187

Max Act: 0.0147. Min Act: -0.0002

Data Index: 708740 (C4 (Web Text))

Max Activating Token Index: 31

Text #13

Max Range: 0.0187. Min Range: -0.0187

Max Act: 0.0152. Min Act: -0.0003

Data Index: 1105647 (C4 (Web Text))

Max Activating Token Index: 169

Text #14

Max Range: 0.0187. Min Range: -0.0187

Max Act: 0.0147. Min Act: -0.0003

Data Index: 522352 (C4 (Web Text))

Max Activating Token Index: 62

Text #15

Max Range: 0.0187. Min Range: -0.0187

Max Act: 0.0146. Min Act: -0.0003

Data Index: 565269 (C4 (Web Text))

Max Activating Token Index: 153

Text #16

Max Range: 0.0187. Min Range: -0.0187

Max Act: 0.0140. Min Act: -0.0003

Data Index: 44334 (C4 (Web Text))

Max Activating Token Index: 293

Text #17

Max Range: 0.0187. Min Range: -0.0187

Max Act: 0.0151. Min Act: -0.0003

Data Index: 662636 (C4 (Web Text))

Max Activating Token Index: 443

Text #18

Max Range: 0.0187. Min Range: -0.0187

Max Act: 0.0140. Min Act: -0.0003

Data Index: 195104 (C4 (Web Text))

Max Activating Token Index: 353

Text #19

Max Range: 0.0187. Min Range: -0.0187

Max Act: 0.0141. Min Act: -0.0003

Data Index: 1095832 (C4 (Web Text))

Max Activating Token Index: 212