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

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

Neuron 1004 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: 0.0202. Min Range: -0.0202

Max Act: 0.0202. Min Act: -0.0006

Data Index: 588542 (C4 (Web Text))

Max Activating Token Index: 492

Text #1

Max Range: 0.0202. Min Range: -0.0202

Max Act: 0.0178. Min Act: -0.0006

Data Index: 15761 (C4 (Web Text))

Max Activating Token Index: 502

Text #2

Max Range: 0.0202. Min Range: -0.0202

Max Act: 0.0193. Min Act: -0.0006

Data Index: 81017 (C4 (Web Text))

Max Activating Token Index: 556

Text #3

Max Range: 0.0202. Min Range: -0.0202

Max Act: 0.0145. Min Act: -0.0006

Data Index: 1198167 (C4 (Web Text))

Max Activating Token Index: 255

Text #4

Max Range: 0.0202. Min Range: -0.0202

Max Act: 0.0175. Min Act: -0.0006

Data Index: 323292 (C4 (Web Text))

Max Activating Token Index: 415

Text #5

Max Range: 0.0202. Min Range: -0.0202

Max Act: 0.0165. Min Act: -0.0006

Data Index: 445801 (C4 (Web Text))

Max Activating Token Index: 132

Text #6

Max Range: 0.0202. Min Range: -0.0202

Max Act: 0.0165. Min Act: -0.0006

Data Index: 61774 (C4 (Web Text))

Max Activating Token Index: 218

Text #7

Max Range: 0.0202. Min Range: -0.0202

Max Act: 0.0180. Min Act: -0.0006

Data Index: 820051 (C4 (Web Text))

Max Activating Token Index: 594

Text #8

Max Range: 0.0202. Min Range: -0.0202

Max Act: 0.0146. Min Act: -0.0006

Data Index: 1346107 (C4 (Web Text))

Max Activating Token Index: 635

Text #9

Max Range: 0.0202. Min Range: -0.0202

Max Act: 0.0171. Min Act: -0.0006

Data Index: 996029 (C4 (Web Text))

Max Activating Token Index: 482

Text #10

Max Range: 0.0202. Min Range: -0.0202

Max Act: 0.0172. Min Act: -0.0006

Data Index: 1117226 (C4 (Web Text))

Max Activating Token Index: 193

Text #11

Max Range: 0.0202. Min Range: -0.0202

Max Act: 0.0172. Min Act: -0.0006

Data Index: 212666 (C4 (Web Text))

Max Activating Token Index: 569

Text #12

Max Range: 0.0202. Min Range: -0.0202

Max Act: 0.0161. Min Act: -0.0006

Data Index: 743252 (C4 (Web Text))

Max Activating Token Index: 595

Text #13

Max Range: 0.0202. Min Range: -0.0202

Max Act: 0.0148. Min Act: -0.0006

Data Index: 140695 (C4 (Web Text))

Max Activating Token Index: 252

Text #14

Max Range: 0.0202. Min Range: -0.0202

Max Act: 0.0148. Min Act: -0.0006

Data Index: 327695 (C4 (Web Text))

Max Activating Token Index: 414

Text #15

Max Range: 0.0202. Min Range: -0.0202

Max Act: 0.0132. Min Act: -0.0006

Data Index: 983889 (C4 (Web Text))

Max Activating Token Index: 125

Text #16

Max Range: 0.0202. Min Range: -0.0202

Max Act: 0.0161. Min Act: -0.0006

Data Index: 576486 (C4 (Web Text))

Max Activating Token Index: 876

Text #17

Max Range: 0.0202. Min Range: -0.0202

Max Act: 0.0161. Min Act: -0.0006

Data Index: 265170 (C4 (Web Text))

Max Activating Token Index: 315

Text #18

Max Range: 0.0202. Min Range: -0.0202

Max Act: 0.0148. Min Act: -0.0006

Data Index: 52206 (C4 (Web Text))

Max Activating Token Index: 609

Text #19

Max Range: 0.0202. Min Range: -0.0202

Max Act: 0.0140. Min Act: -0.0006

Data Index: 1148841 (C4 (Web Text))

Max Activating Token Index: 442