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

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

Neuron 3860 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: 0.0172. Min Range: -0.0172

Max Act: 0.0169. Min Act: -0.0003

Data Index: 224963 (C4 (Web Text))

Max Activating Token Index: 400

Text #1

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0172. Min Act: -0.0003

Data Index: 599368 (C4 (Web Text))

Max Activating Token Index: 21

Text #2

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0158. Min Act: -0.0004

Data Index: 37412 (C4 (Web Text))

Max Activating Token Index: 913

Text #3

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0165. Min Act: -0.0003

Data Index: 132691 (C4 (Web Text))

Max Activating Token Index: 740

Text #4

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0158. Min Act: -0.0004

Data Index: 1163024 (C4 (Web Text))

Max Activating Token Index: 602

Text #5

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0144. Min Act: -0.0003

Data Index: 651457 (C4 (Web Text))

Max Activating Token Index: 694

Text #6

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0150. Min Act: -0.0003

Data Index: 1060238 (C4 (Web Text))

Max Activating Token Index: 408

Text #7

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0154. Min Act: -0.0003

Data Index: 564666 (C4 (Web Text))

Max Activating Token Index: 963

Text #8

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0150. Min Act: -0.0003

Data Index: 1209459 (C4 (Web Text))

Max Activating Token Index: 299

Text #9

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0153. Min Act: -0.0003

Data Index: 848676 (C4 (Web Text))

Max Activating Token Index: 109

Text #10

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0150. Min Act: -0.0003

Data Index: 1094997 (C4 (Web Text))

Max Activating Token Index: 997

Text #11

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0144. Min Act: -0.0003

Data Index: 166699 (C4 (Web Text))

Max Activating Token Index: 664

Text #12

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0150. Min Act: -0.0004

Data Index: 822672 (C4 (Web Text))

Max Activating Token Index: 670

Text #13

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0147. Min Act: -0.0003

Data Index: 957581 (C4 (Web Text))

Max Activating Token Index: 197

Text #14

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0146. Min Act: -0.0003

Data Index: 1244412 (C4 (Web Text))

Max Activating Token Index: 621

Text #15

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0140. Min Act: -0.0003

Data Index: 74058 (C4 (Web Text))

Max Activating Token Index: 40

Text #16

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0142. Min Act: -0.0003

Data Index: 55668 (C4 (Web Text))

Max Activating Token Index: 910

Text #17

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0147. Min Act: -0.0003

Data Index: 1303867 (C4 (Web Text))

Max Activating Token Index: 582

Text #18

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0131. Min Act: -0.0003

Data Index: 644934 (C4 (Web Text))

Max Activating Token Index: 153

Text #19

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0134. Min Act: -0.0003

Data Index: 271404 (C4 (Web Text))

Max Activating Token Index: 390