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

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

Neuron 1678 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: 0.0170. Min Range: -0.0170

Max Act: 0.0170. Min Act: -0.0003

Data Index: 965498 (C4 (Web Text))

Max Activating Token Index: 193

Text #1

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0152. Min Act: -0.0003

Data Index: 1378297 (Python Code)

Max Activating Token Index: 227

Text #2

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0151. Min Act: -0.0003

Data Index: 1328456 (C4 (Web Text))

Max Activating Token Index: 366

Text #3

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0152. Min Act: -0.0003

Data Index: 330078 (C4 (Web Text))

Max Activating Token Index: 280

Text #4

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0143. Min Act: -0.0003

Data Index: 1109723 (C4 (Web Text))

Max Activating Token Index: 670

Text #5

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0138. Min Act: -0.0004

Data Index: 1069781 (C4 (Web Text))

Max Activating Token Index: 531

Text #6

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0138. Min Act: -0.0003

Data Index: 157277 (C4 (Web Text))

Max Activating Token Index: 286

Text #7

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0135. Min Act: -0.0004

Data Index: 121203 (C4 (Web Text))

Max Activating Token Index: 630

Text #8

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0134. Min Act: -0.0004

Data Index: 1212014 (C4 (Web Text))

Max Activating Token Index: 490

Text #9

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0133. Min Act: -0.0003

Data Index: 707986 (C4 (Web Text))

Max Activating Token Index: 346

Text #10

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0132. Min Act: -0.0003

Data Index: 1033580 (C4 (Web Text))

Max Activating Token Index: 418

Text #11

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0130. Min Act: -0.0004

Data Index: 1053257 (C4 (Web Text))

Max Activating Token Index: 136

Text #12

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0129. Min Act: -0.0003

Data Index: 857710 (C4 (Web Text))

Max Activating Token Index: 150

Text #13

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0129. Min Act: -0.0004

Data Index: 831984 (C4 (Web Text))

Max Activating Token Index: 321

Text #14

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0128. Min Act: -0.0003

Data Index: 502002 (C4 (Web Text))

Max Activating Token Index: 332

Text #15

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0127. Min Act: -0.0003

Data Index: 1578773 (Python Code)

Max Activating Token Index: 191

Text #16

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0129. Min Act: -0.0004

Data Index: 1162080 (C4 (Web Text))

Max Activating Token Index: 233

Text #17

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0126. Min Act: -0.0004

Data Index: 204083 (C4 (Web Text))

Max Activating Token Index: 500

Text #18

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0122. Min Act: -0.0003

Data Index: 1646390 (Python Code)

Max Activating Token Index: 100

Text #19

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0126. Min Act: -0.0003

Data Index: 910475 (C4 (Web Text))

Max Activating Token Index: 366