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

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

Neuron 1411 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0157. Min Act: -0.0006

Data Index: 176704 (C4 (Web Text))

Max Activating Token Index: 671

Text #1

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0164. Min Act: -0.0006

Data Index: 607384 (C4 (Web Text))

Max Activating Token Index: 654

Text #2

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0149. Min Act: -0.0006

Data Index: 959239 (C4 (Web Text))

Max Activating Token Index: 967

Text #3

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0149. Min Act: -0.0006

Data Index: 377814 (C4 (Web Text))

Max Activating Token Index: 200

Text #4

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0144. Min Act: -0.0006

Data Index: 682967 (C4 (Web Text))

Max Activating Token Index: 774

Text #5

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0139. Min Act: -0.0006

Data Index: 31997 (C4 (Web Text))

Max Activating Token Index: 419

Text #6

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0141. Min Act: -0.0006

Data Index: 262629 (C4 (Web Text))

Max Activating Token Index: 357

Text #7

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0141. Min Act: -0.0006

Data Index: 389466 (C4 (Web Text))

Max Activating Token Index: 133

Text #8

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0146. Min Act: -0.0006

Data Index: 91919 (C4 (Web Text))

Max Activating Token Index: 977

Text #9

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0139. Min Act: -0.0006

Data Index: 326218 (C4 (Web Text))

Max Activating Token Index: 459

Text #10

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0138. Min Act: -0.0005

Data Index: 444856 (C4 (Web Text))

Max Activating Token Index: 186

Text #11

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0138. Min Act: -0.0006

Data Index: 970326 (C4 (Web Text))

Max Activating Token Index: 646

Text #12

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0134. Min Act: -0.0006

Data Index: 243542 (C4 (Web Text))

Max Activating Token Index: 983

Text #13

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0136. Min Act: -0.0006

Data Index: 383823 (C4 (Web Text))

Max Activating Token Index: 387

Text #14

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0135. Min Act: -0.0006

Data Index: 855232 (C4 (Web Text))

Max Activating Token Index: 962

Text #15

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0135. Min Act: -0.0006

Data Index: 666302 (C4 (Web Text))

Max Activating Token Index: 716

Text #16

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0140. Min Act: -0.0006

Data Index: 286475 (C4 (Web Text))

Max Activating Token Index: 571

Text #17

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0133. Min Act: -0.0006

Data Index: 915447 (C4 (Web Text))

Max Activating Token Index: 805

Text #18

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0132. Min Act: -0.0006

Data Index: 310474 (C4 (Web Text))

Max Activating Token Index: 439

Text #19

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0134. Min Act: -0.0006

Data Index: 1205178 (C4 (Web Text))

Max Activating Token Index: 576