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

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

Neuron 2710 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0196. Min Act: -0.0001

Data Index: 118124 (C4 (Web Text))

Max Activating Token Index: 104

Text #1

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0169. Min Act: -0.0001

Data Index: 1317166 (C4 (Web Text))

Max Activating Token Index: 942

Text #2

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0179. Min Act: -0.0001

Data Index: 1243542 (C4 (Web Text))

Max Activating Token Index: 34

Text #3

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0174. Min Act: -0.0001

Data Index: 699676 (C4 (Web Text))

Max Activating Token Index: 700

Text #4

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0167. Min Act: -0.0001

Data Index: 188913 (C4 (Web Text))

Max Activating Token Index: 997

Text #5

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0168. Min Act: -0.0001

Data Index: 1013444 (C4 (Web Text))

Max Activating Token Index: 456

Text #6

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0155. Min Act: -0.0001

Data Index: 81662 (C4 (Web Text))

Max Activating Token Index: 49

Text #7

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0165. Min Act: -0.0001

Data Index: 444807 (C4 (Web Text))

Max Activating Token Index: 603

Text #8

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0167. Min Act: -0.0001

Data Index: 379388 (C4 (Web Text))

Max Activating Token Index: 39

Text #9

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0143. Min Act: -0.0001

Data Index: 1315914 (C4 (Web Text))

Max Activating Token Index: 693

Text #10

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0156. Min Act: -0.0001

Data Index: 1312031 (C4 (Web Text))

Max Activating Token Index: 49

Text #11

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0157. Min Act: -0.0001

Data Index: 512583 (C4 (Web Text))

Max Activating Token Index: 730

Text #12

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0162. Min Act: -0.0001

Data Index: 604881 (C4 (Web Text))

Max Activating Token Index: 203

Text #13

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0147. Min Act: -0.0001

Data Index: 107139 (C4 (Web Text))

Max Activating Token Index: 22

Text #14

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0190. Min Act: -0.0001

Data Index: 240295 (C4 (Web Text))

Max Activating Token Index: 286

Text #15

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0159. Min Act: -0.0001

Data Index: 495919 (C4 (Web Text))

Max Activating Token Index: 670

Text #16

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0164. Min Act: -0.0001

Data Index: 803543 (C4 (Web Text))

Max Activating Token Index: 91

Text #17

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0163. Min Act: -0.0001

Data Index: 93264 (C4 (Web Text))

Max Activating Token Index: 16

Text #18

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0162. Min Act: -0.0001

Data Index: 849562 (C4 (Web Text))

Max Activating Token Index: 750

Text #19

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0151. Min Act: -0.0001

Data Index: 467050 (C4 (Web Text))

Max Activating Token Index: 633