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

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

Neuron 1997 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: 687034 (C4 (Web Text))

Max Activating Token Index: 449

Text #1

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0162. Min Act: -0.0006

Data Index: 1612063 (Python Code)

Max Activating Token Index: 178

Text #2

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0158. Min Act: -0.0006

Data Index: 1158150 (C4 (Web Text))

Max Activating Token Index: 1009

Text #3

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0155. Min Act: -0.0006

Data Index: 562090 (C4 (Web Text))

Max Activating Token Index: 45

Text #4

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0148. Min Act: -0.0006

Data Index: 54199 (C4 (Web Text))

Max Activating Token Index: 153

Text #5

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0144. Min Act: -0.0006

Data Index: 1170630 (C4 (Web Text))

Max Activating Token Index: 786

Text #6

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0149. Min Act: -0.0006

Data Index: 912676 (C4 (Web Text))

Max Activating Token Index: 992

Text #7

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0146. Min Act: -0.0006

Data Index: 19431 (C4 (Web Text))

Max Activating Token Index: 5

Text #8

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0144. Min Act: -0.0006

Data Index: 625476 (C4 (Web Text))

Max Activating Token Index: 796

Text #9

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0139. Min Act: -0.0006

Data Index: 643544 (C4 (Web Text))

Max Activating Token Index: 461

Text #10

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0142. Min Act: -0.0006

Data Index: 576488 (C4 (Web Text))

Max Activating Token Index: 260

Text #11

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0145. Min Act: -0.0006

Data Index: 289400 (C4 (Web Text))

Max Activating Token Index: 607

Text #12

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0159. Min Act: -0.0006

Data Index: 200260 (C4 (Web Text))

Max Activating Token Index: 714

Text #13

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0137. Min Act: -0.0006

Data Index: 863085 (C4 (Web Text))

Max Activating Token Index: 759

Text #14

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0133. Min Act: -0.0006

Data Index: 1168875 (C4 (Web Text))

Max Activating Token Index: 103

Text #15

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0126. Min Act: -0.0006

Data Index: 1154386 (C4 (Web Text))

Max Activating Token Index: 631

Text #16

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0135. Min Act: -0.0006

Data Index: 546564 (C4 (Web Text))

Max Activating Token Index: 167

Text #17

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0139. Min Act: -0.0006

Data Index: 701521 (C4 (Web Text))

Max Activating Token Index: 838

Text #18

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0134. Min Act: -0.0006

Data Index: 915182 (C4 (Web Text))

Max Activating Token Index: 925

Text #19

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0130. Min Act: -0.0006

Data Index: 633807 (C4 (Web Text))

Max Activating Token Index: 445