Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2289 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0163. Min Act: -0.0003

Data Index: 825614 (C4 (Web Text))

Max Activating Token Index: 426

Text #1

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0155. Min Act: -0.0002

Data Index: 1426581 (Python Code)

Max Activating Token Index: 382

Text #2

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0154. Min Act: -0.0003

Data Index: 1372376 (Python Code)

Max Activating Token Index: 69

Text #3

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0151. Min Act: -0.0003

Data Index: 1164948 (C4 (Web Text))

Max Activating Token Index: 255

Text #4

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0148. Min Act: -0.0003

Data Index: 12687 (C4 (Web Text))

Max Activating Token Index: 288

Text #5

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0151. Min Act: -0.0003

Data Index: 734396 (C4 (Web Text))

Max Activating Token Index: 309

Text #6

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0143. Min Act: -0.0003

Data Index: 492114 (C4 (Web Text))

Max Activating Token Index: 277

Text #7

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0146. Min Act: -0.0003

Data Index: 145612 (C4 (Web Text))

Max Activating Token Index: 755

Text #8

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0149. Min Act: -0.0003

Data Index: 196667 (C4 (Web Text))

Max Activating Token Index: 57

Text #9

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0146. Min Act: -0.0003

Data Index: 231375 (C4 (Web Text))

Max Activating Token Index: 613

Text #10

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0145. Min Act: -0.0003

Data Index: 873151 (C4 (Web Text))

Max Activating Token Index: 264

Text #11

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0144. Min Act: -0.0003

Data Index: 187284 (C4 (Web Text))

Max Activating Token Index: 870

Text #12

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0144. Min Act: -0.0003

Data Index: 883422 (C4 (Web Text))

Max Activating Token Index: 783

Text #13

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0144. Min Act: -0.0003

Data Index: 1575905 (Python Code)

Max Activating Token Index: 260

Text #14

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0142. Min Act: -0.0003

Data Index: 103839 (C4 (Web Text))

Max Activating Token Index: 206

Text #15

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0141. Min Act: -0.0003

Data Index: 1177794 (C4 (Web Text))

Max Activating Token Index: 568

Text #16

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0140. Min Act: -0.0003

Data Index: 1379274 (Python Code)

Max Activating Token Index: 968

Text #17

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0139. Min Act: -0.0003

Data Index: 397551 (C4 (Web Text))

Max Activating Token Index: 365

Text #18

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0139. Min Act: -0.0003

Data Index: 218636 (C4 (Web Text))

Max Activating Token Index: 218

Text #19

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0135. Min Act: -0.0004

Data Index: 503707 (C4 (Web Text))

Max Activating Token Index: 882