Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 545 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0252. Min Act: -0.0002

Data Index: 1651102 (Python Code)

Max Activating Token Index: 275

Text #1

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0219. Min Act: -0.0002

Data Index: 1605105 (Python Code)

Max Activating Token Index: 644

Text #2

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0209. Min Act: -0.0003

Data Index: 543836 (C4 (Web Text))

Max Activating Token Index: 673

Text #3

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0186. Min Act: -0.0002

Data Index: 1541774 (Python Code)

Max Activating Token Index: 601

Text #4

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0177. Min Act: -0.0003

Data Index: 999288 (C4 (Web Text))

Max Activating Token Index: 292

Text #5

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0175. Min Act: -0.0002

Data Index: 1402370 (Python Code)

Max Activating Token Index: 312

Text #6

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0173. Min Act: -0.0002

Data Index: 651195 (C4 (Web Text))

Max Activating Token Index: 526

Text #7

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0172. Min Act: -0.0002

Data Index: 1625108 (Python Code)

Max Activating Token Index: 104

Text #8

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0170. Min Act: -0.0003

Data Index: 137179 (C4 (Web Text))

Max Activating Token Index: 393

Text #9

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0168. Min Act: -0.0003

Data Index: 416455 (C4 (Web Text))

Max Activating Token Index: 810

Text #10

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0168. Min Act: -0.0002

Data Index: 1395325 (Python Code)

Max Activating Token Index: 59

Text #11

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0162. Min Act: -0.0002

Data Index: 1397591 (Python Code)

Max Activating Token Index: 234

Text #12

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0167. Min Act: -0.0003

Data Index: 1026652 (C4 (Web Text))

Max Activating Token Index: 711

Text #13

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0167. Min Act: -0.0003

Data Index: 685089 (C4 (Web Text))

Max Activating Token Index: 811

Text #14

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0160. Min Act: -0.0003

Data Index: 893417 (C4 (Web Text))

Max Activating Token Index: 184

Text #15

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0159. Min Act: -0.0002

Data Index: 1493132 (Python Code)

Max Activating Token Index: 727

Text #16

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0158. Min Act: -0.0002

Data Index: 1472094 (Python Code)

Max Activating Token Index: 46

Text #17

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0155. Min Act: -0.0002

Data Index: 1440252 (Python Code)

Max Activating Token Index: 154

Text #18

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0152. Min Act: -0.0003

Data Index: 1343607 (C4 (Web Text))

Max Activating Token Index: 535

Text #19

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0158. Min Act: -0.0002

Data Index: 217389 (C4 (Web Text))

Max Activating Token Index: 576