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

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

Neuron 224 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: 0.0177. Min Range: -0.0177

Max Act: 0.0177. Min Act: -0.0006

Data Index: 1023501 (C4 (Web Text))

Max Activating Token Index: 910

Text #1

Max Range: 0.0177. Min Range: -0.0177

Max Act: 0.0173. Min Act: -0.0006

Data Index: 139728 (C4 (Web Text))

Max Activating Token Index: 535

Text #2

Max Range: 0.0177. Min Range: -0.0177

Max Act: 0.0162. Min Act: -0.0006

Data Index: 820422 (C4 (Web Text))

Max Activating Token Index: 852

Text #3

Max Range: 0.0177. Min Range: -0.0177

Max Act: 0.0158. Min Act: -0.0006

Data Index: 148087 (C4 (Web Text))

Max Activating Token Index: 451

Text #4

Max Range: 0.0177. Min Range: -0.0177

Max Act: 0.0155. Min Act: -0.0006

Data Index: 455200 (C4 (Web Text))

Max Activating Token Index: 515

Text #5

Max Range: 0.0177. Min Range: -0.0177

Max Act: 0.0159. Min Act: -0.0006

Data Index: 283837 (C4 (Web Text))

Max Activating Token Index: 379

Text #6

Max Range: 0.0177. Min Range: -0.0177

Max Act: 0.0155. Min Act: -0.0006

Data Index: 19024 (C4 (Web Text))

Max Activating Token Index: 335

Text #7

Max Range: 0.0177. Min Range: -0.0177

Max Act: 0.0150. Min Act: -0.0006

Data Index: 202067 (C4 (Web Text))

Max Activating Token Index: 489

Text #8

Max Range: 0.0177. Min Range: -0.0177

Max Act: 0.0146. Min Act: -0.0006

Data Index: 1178522 (C4 (Web Text))

Max Activating Token Index: 920

Text #9

Max Range: 0.0177. Min Range: -0.0177

Max Act: 0.0155. Min Act: -0.0006

Data Index: 926633 (C4 (Web Text))

Max Activating Token Index: 920

Text #10

Max Range: 0.0177. Min Range: -0.0177

Max Act: 0.0146. Min Act: -0.0006

Data Index: 144473 (C4 (Web Text))

Max Activating Token Index: 152

Text #11

Max Range: 0.0177. Min Range: -0.0177

Max Act: 0.0148. Min Act: -0.0006

Data Index: 215284 (C4 (Web Text))

Max Activating Token Index: 183

Text #12

Max Range: 0.0177. Min Range: -0.0177

Max Act: 0.0150. Min Act: -0.0006

Data Index: 1307171 (C4 (Web Text))

Max Activating Token Index: 358

Text #13

Max Range: 0.0177. Min Range: -0.0177

Max Act: 0.0142. Min Act: -0.0006

Data Index: 811202 (C4 (Web Text))

Max Activating Token Index: 967

Text #14

Max Range: 0.0177. Min Range: -0.0177

Max Act: 0.0146. Min Act: -0.0006

Data Index: 418447 (C4 (Web Text))

Max Activating Token Index: 450

Text #15

Max Range: 0.0177. Min Range: -0.0177

Max Act: 0.0146. Min Act: -0.0006

Data Index: 271057 (C4 (Web Text))

Max Activating Token Index: 398

Text #16

Max Range: 0.0177. Min Range: -0.0177

Max Act: 0.0143. Min Act: -0.0006

Data Index: 150944 (C4 (Web Text))

Max Activating Token Index: 961

Text #17

Max Range: 0.0177. Min Range: -0.0177

Max Act: 0.0145. Min Act: -0.0006

Data Index: 185287 (C4 (Web Text))

Max Activating Token Index: 150

Text #18

Max Range: 0.0177. Min Range: -0.0177

Max Act: 0.0141. Min Act: -0.0006

Data Index: 808745 (C4 (Web Text))

Max Activating Token Index: 546

Text #19

Max Range: 0.0177. Min Range: -0.0177

Max Act: 0.0142. Min Act: -0.0006

Data Index: 839687 (C4 (Web Text))

Max Activating Token Index: 530