Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 927 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0196. Min Act: -0.0006

Data Index: 1023705 (C4 (Web Text))

Max Activating Token Index: 583

Text #1

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0162. Min Act: -0.0006

Data Index: 500582 (C4 (Web Text))

Max Activating Token Index: 483

Text #2

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0164. Min Act: -0.0006

Data Index: 913388 (C4 (Web Text))

Max Activating Token Index: 324

Text #3

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0158. Min Act: -0.0006

Data Index: 470148 (C4 (Web Text))

Max Activating Token Index: 834

Text #4

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0153. Min Act: -0.0006

Data Index: 1052232 (C4 (Web Text))

Max Activating Token Index: 126

Text #5

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0152. Min Act: -0.0006

Data Index: 511564 (C4 (Web Text))

Max Activating Token Index: 421

Text #6

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0148. Min Act: -0.0006

Data Index: 285453 (C4 (Web Text))

Max Activating Token Index: 105

Text #7

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0143. Min Act: -0.0006

Data Index: 885041 (C4 (Web Text))

Max Activating Token Index: 911

Text #8

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0144. Min Act: -0.0006

Data Index: 1607257 (Python Code)

Max Activating Token Index: 169

Text #9

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0143. Min Act: -0.0006

Data Index: 591476 (C4 (Web Text))

Max Activating Token Index: 336

Text #10

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0137. Min Act: -0.0006

Data Index: 1282308 (C4 (Web Text))

Max Activating Token Index: 996

Text #11

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0138. Min Act: -0.0006

Data Index: 983928 (C4 (Web Text))

Max Activating Token Index: 1009

Text #12

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0141. Min Act: -0.0006

Data Index: 953298 (C4 (Web Text))

Max Activating Token Index: 981

Text #13

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0134. Min Act: -0.0006

Data Index: 807457 (C4 (Web Text))

Max Activating Token Index: 823

Text #14

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0133. Min Act: -0.0006

Data Index: 347892 (C4 (Web Text))

Max Activating Token Index: 895

Text #15

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0136. Min Act: -0.0006

Data Index: 1234739 (C4 (Web Text))

Max Activating Token Index: 152

Text #16

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0136. Min Act: -0.0006

Data Index: 1409922 (Python Code)

Max Activating Token Index: 137

Text #17

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0132. Min Act: -0.0006

Data Index: 1481379 (Python Code)

Max Activating Token Index: 654

Text #18

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0132. Min Act: -0.0006

Data Index: 552170 (C4 (Web Text))

Max Activating Token Index: 207

Text #19

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0135. Min Act: -0.0006

Data Index: 359326 (C4 (Web Text))

Max Activating Token Index: 225