Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2636 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0161. Min Act: -0.0002

Data Index: 811056 (C4 (Web Text))

Max Activating Token Index: 939

Text #1

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0160. Min Act: -0.0002

Data Index: 528308 (C4 (Web Text))

Max Activating Token Index: 340

Text #2

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0160. Min Act: -0.0002

Data Index: 1461889 (Python Code)

Max Activating Token Index: 1000

Text #3

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0157. Min Act: -0.0002

Data Index: 1355729 (C4 (Web Text))

Max Activating Token Index: 173

Text #4

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0153. Min Act: -0.0002

Data Index: 545542 (C4 (Web Text))

Max Activating Token Index: 997

Text #5

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0151. Min Act: -0.0002

Data Index: 1318848 (C4 (Web Text))

Max Activating Token Index: 309

Text #6

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0148. Min Act: -0.0002

Data Index: 202349 (C4 (Web Text))

Max Activating Token Index: 490

Text #7

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0147. Min Act: -0.0002

Data Index: 1536735 (Python Code)

Max Activating Token Index: 40

Text #8

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0147. Min Act: -0.0002

Data Index: 1174157 (C4 (Web Text))

Max Activating Token Index: 770

Text #9

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0147. Min Act: -0.0002

Data Index: 818602 (C4 (Web Text))

Max Activating Token Index: 257

Text #10

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0144. Min Act: -0.0002

Data Index: 69590 (C4 (Web Text))

Max Activating Token Index: 658

Text #11

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0146. Min Act: -0.0002

Data Index: 66407 (C4 (Web Text))

Max Activating Token Index: 245

Text #12

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0143. Min Act: -0.0002

Data Index: 1249160 (C4 (Web Text))

Max Activating Token Index: 142

Text #13

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0149. Min Act: -0.0002

Data Index: 290340 (C4 (Web Text))

Max Activating Token Index: 452

Text #14

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0146. Min Act: -0.0002

Data Index: 225757 (C4 (Web Text))

Max Activating Token Index: 1014

Text #15

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0142. Min Act: -0.0002

Data Index: 1479519 (Python Code)

Max Activating Token Index: 18

Text #16

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0145. Min Act: -0.0002

Data Index: 1620925 (Python Code)

Max Activating Token Index: 8

Text #17

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0145. Min Act: -0.0002

Data Index: 1581665 (Python Code)

Max Activating Token Index: 123

Text #18

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0147. Min Act: -0.0001

Data Index: 1567366 (Python Code)

Max Activating Token Index: 371

Text #19

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0144. Min Act: -0.0002

Data Index: 1394661 (Python Code)

Max Activating Token Index: 608