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

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

Neuron 507 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: 0.0186. Min Range: -0.0186

Max Act: 0.0186. Min Act: -0.0006

Data Index: 737909 (C4 (Web Text))

Max Activating Token Index: 107

Text #1

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0170. Min Act: -0.0006

Data Index: 588966 (C4 (Web Text))

Max Activating Token Index: 375

Text #2

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0149. Min Act: -0.0006

Data Index: 700751 (C4 (Web Text))

Max Activating Token Index: 979

Text #3

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0159. Min Act: -0.0006

Data Index: 545475 (C4 (Web Text))

Max Activating Token Index: 939

Text #4

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0148. Min Act: -0.0006

Data Index: 1082132 (C4 (Web Text))

Max Activating Token Index: 250

Text #5

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0170. Min Act: -0.0006

Data Index: 1067775 (C4 (Web Text))

Max Activating Token Index: 986

Text #6

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0159. Min Act: -0.0006

Data Index: 1145484 (C4 (Web Text))

Max Activating Token Index: 662

Text #7

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0162. Min Act: -0.0006

Data Index: 731766 (C4 (Web Text))

Max Activating Token Index: 325

Text #8

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0154. Min Act: -0.0006

Data Index: 374906 (C4 (Web Text))

Max Activating Token Index: 598

Text #9

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0154. Min Act: -0.0006

Data Index: 608833 (C4 (Web Text))

Max Activating Token Index: 944

Text #10

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0153. Min Act: -0.0006

Data Index: 1126855 (C4 (Web Text))

Max Activating Token Index: 644

Text #11

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0142. Min Act: -0.0006

Data Index: 1324748 (C4 (Web Text))

Max Activating Token Index: 810

Text #12

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0134. Min Act: -0.0006

Data Index: 1010055 (C4 (Web Text))

Max Activating Token Index: 649

Text #13

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0146. Min Act: -0.0006

Data Index: 737248 (C4 (Web Text))

Max Activating Token Index: 822

Text #14

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0145. Min Act: -0.0006

Data Index: 1310049 (C4 (Web Text))

Max Activating Token Index: 108

Text #15

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0129. Min Act: -0.0006

Data Index: 1041645 (C4 (Web Text))

Max Activating Token Index: 807

Text #16

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0138. Min Act: -0.0006

Data Index: 659637 (C4 (Web Text))

Max Activating Token Index: 491

Text #17

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0135. Min Act: -0.0006

Data Index: 1341139 (C4 (Web Text))

Max Activating Token Index: 609

Text #18

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0146. Min Act: -0.0006

Data Index: 398807 (C4 (Web Text))

Max Activating Token Index: 519

Text #19

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0127. Min Act: -0.0006

Data Index: 225240 (C4 (Web Text))

Max Activating Token Index: 874