Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 850 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0168. Min Act: -0.0006

Data Index: 1195578 (C4 (Web Text))

Max Activating Token Index: 959

Text #1

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0168. Min Act: -0.0006

Data Index: 886191 (C4 (Web Text))

Max Activating Token Index: 694

Text #2

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0147. Min Act: -0.0006

Data Index: 91781 (C4 (Web Text))

Max Activating Token Index: 295

Text #3

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0153. Min Act: -0.0006

Data Index: 1304640 (C4 (Web Text))

Max Activating Token Index: 383

Text #4

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0141. Min Act: -0.0006

Data Index: 740216 (C4 (Web Text))

Max Activating Token Index: 610

Text #5

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0151. Min Act: -0.0006

Data Index: 582234 (C4 (Web Text))

Max Activating Token Index: 812

Text #6

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0145. Min Act: -0.0006

Data Index: 174011 (C4 (Web Text))

Max Activating Token Index: 238

Text #7

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0148. Min Act: -0.0006

Data Index: 24088 (C4 (Web Text))

Max Activating Token Index: 5

Text #8

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0145. Min Act: -0.0006

Data Index: 486484 (C4 (Web Text))

Max Activating Token Index: 244

Text #9

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0137. Min Act: -0.0006

Data Index: 693464 (C4 (Web Text))

Max Activating Token Index: 562

Text #10

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0148. Min Act: -0.0006

Data Index: 1102841 (C4 (Web Text))

Max Activating Token Index: 339

Text #11

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0143. Min Act: -0.0006

Data Index: 1122654 (C4 (Web Text))

Max Activating Token Index: 683

Text #12

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0140. Min Act: -0.0006

Data Index: 597890 (C4 (Web Text))

Max Activating Token Index: 46

Text #13

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0137. Min Act: -0.0006

Data Index: 225734 (C4 (Web Text))

Max Activating Token Index: 474

Text #14

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0158. Min Act: -0.0006

Data Index: 56634 (C4 (Web Text))

Max Activating Token Index: 640

Text #15

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0134. Min Act: -0.0006

Data Index: 903106 (C4 (Web Text))

Max Activating Token Index: 51

Text #16

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0134. Min Act: -0.0006

Data Index: 787518 (C4 (Web Text))

Max Activating Token Index: 74

Text #17

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0133. Min Act: -0.0006

Data Index: 985657 (C4 (Web Text))

Max Activating Token Index: 840

Text #18

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0139. Min Act: -0.0006

Data Index: 862385 (C4 (Web Text))

Max Activating Token Index: 192

Text #19

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0129. Min Act: -0.0006

Data Index: 1322776 (C4 (Web Text))

Max Activating Token Index: 714