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

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

Neuron 946 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: 0.0153. Min Range: -0.0153

Max Act: 0.0147. Min Act: -0.0006

Data Index: 205060 (C4 (Web Text))

Max Activating Token Index: 5

Text #1

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0146. Min Act: -0.0006

Data Index: 198019 (C4 (Web Text))

Max Activating Token Index: 23

Text #2

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0146. Min Act: -0.0006

Data Index: 168095 (C4 (Web Text))

Max Activating Token Index: 174

Text #3

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0140. Min Act: -0.0006

Data Index: 1291480 (C4 (Web Text))

Max Activating Token Index: 152

Text #4

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0139. Min Act: -0.0006

Data Index: 680494 (C4 (Web Text))

Max Activating Token Index: 205

Text #5

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0153. Min Act: -0.0006

Data Index: 401014 (C4 (Web Text))

Max Activating Token Index: 454

Text #6

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0134. Min Act: -0.0006

Data Index: 679967 (C4 (Web Text))

Max Activating Token Index: 241

Text #7

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0144. Min Act: -0.0006

Data Index: 566643 (C4 (Web Text))

Max Activating Token Index: 233

Text #8

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0144. Min Act: -0.0006

Data Index: 721965 (C4 (Web Text))

Max Activating Token Index: 16

Text #9

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0140. Min Act: -0.0006

Data Index: 254994 (C4 (Web Text))

Max Activating Token Index: 149

Text #10

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0143. Min Act: -0.0006

Data Index: 1015047 (C4 (Web Text))

Max Activating Token Index: 58

Text #11

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0129. Min Act: -0.0006

Data Index: 810382 (C4 (Web Text))

Max Activating Token Index: 282

Text #12

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0138. Min Act: -0.0006

Data Index: 990324 (C4 (Web Text))

Max Activating Token Index: 108

Text #13

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0132. Min Act: -0.0006

Data Index: 687266 (C4 (Web Text))

Max Activating Token Index: 315

Text #14

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0141. Min Act: -0.0006

Data Index: 165091 (C4 (Web Text))

Max Activating Token Index: 308

Text #15

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0134. Min Act: -0.0006

Data Index: 1183367 (C4 (Web Text))

Max Activating Token Index: 20

Text #16

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0134. Min Act: -0.0006

Data Index: 686348 (C4 (Web Text))

Max Activating Token Index: 150

Text #17

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0134. Min Act: -0.0006

Data Index: 787542 (C4 (Web Text))

Max Activating Token Index: 207

Text #18

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0131. Min Act: -0.0006

Data Index: 1033059 (C4 (Web Text))

Max Activating Token Index: 36

Text #19

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0133. Min Act: -0.0006

Data Index: 1220335 (C4 (Web Text))

Max Activating Token Index: 964