Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1722 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2477. Min Range: -0.2477

Max Act: 0.2477. Min Act: -0.0003

Data Index: 1337865 (C4 (Web Text))

Max Activating Token Index: 855

Text #1

Max Range: 0.2477. Min Range: -0.2477

Max Act: 0.2357. Min Act: -0.0003

Data Index: 1279053 (C4 (Web Text))

Max Activating Token Index: 900

Text #2

Max Range: 0.2477. Min Range: -0.2477

Max Act: 0.2400. Min Act: -0.0003

Data Index: 1116758 (C4 (Web Text))

Max Activating Token Index: 686

Text #3

Max Range: 0.2477. Min Range: -0.2477

Max Act: 0.2407. Min Act: -0.0003

Data Index: 259577 (C4 (Web Text))

Max Activating Token Index: 690

Text #4

Max Range: 0.2477. Min Range: -0.2477

Max Act: 0.2160. Min Act: -0.0003

Data Index: 1030190 (C4 (Web Text))

Max Activating Token Index: 565

Text #5

Max Range: 0.2477. Min Range: -0.2477

Max Act: 0.2262. Min Act: -0.0003

Data Index: 45343 (C4 (Web Text))

Max Activating Token Index: 401

Text #6

Max Range: 0.2477. Min Range: -0.2477

Max Act: 0.2180. Min Act: -0.0003

Data Index: 285242 (C4 (Web Text))

Max Activating Token Index: 846

Text #7

Max Range: 0.2477. Min Range: -0.2477

Max Act: 0.2249. Min Act: -0.0003

Data Index: 102594 (C4 (Web Text))

Max Activating Token Index: 195

Text #8

Max Range: 0.2477. Min Range: -0.2477

Max Act: 0.2183. Min Act: -0.0003

Data Index: 742235 (C4 (Web Text))

Max Activating Token Index: 161

Text #9

Max Range: 0.2477. Min Range: -0.2477

Max Act: 0.2148. Min Act: -0.0003

Data Index: 1358144 (C4 (Web Text))

Max Activating Token Index: 795

Text #10

Max Range: 0.2477. Min Range: -0.2477

Max Act: 0.2046. Min Act: -0.0003

Data Index: 331175 (C4 (Web Text))

Max Activating Token Index: 364

Text #11

Max Range: 0.2477. Min Range: -0.2477

Max Act: 0.2256. Min Act: -0.0003

Data Index: 839438 (C4 (Web Text))

Max Activating Token Index: 469

Text #12

Max Range: 0.2477. Min Range: -0.2477

Max Act: 0.2230. Min Act: -0.0003

Data Index: 1105272 (C4 (Web Text))

Max Activating Token Index: 414

Text #13

Max Range: 0.2477. Min Range: -0.2477

Max Act: 0.1995. Min Act: -0.0003

Data Index: 615690 (C4 (Web Text))

Max Activating Token Index: 8

Text #14

Max Range: 0.2477. Min Range: -0.2477

Max Act: 0.1845. Min Act: -0.0003

Data Index: 837211 (C4 (Web Text))

Max Activating Token Index: 142

Text #15

Max Range: 0.2477. Min Range: -0.2477

Max Act: 0.1843. Min Act: -0.0003

Data Index: 932451 (C4 (Web Text))

Max Activating Token Index: 206

Text #16

Max Range: 0.2477. Min Range: -0.2477

Max Act: 0.1880. Min Act: -0.0003

Data Index: 448642 (C4 (Web Text))

Max Activating Token Index: 54

Text #17

Max Range: 0.2477. Min Range: -0.2477

Max Act: 0.1804. Min Act: -0.0003

Data Index: 1262243 (C4 (Web Text))

Max Activating Token Index: 352

Text #18

Max Range: 0.2477. Min Range: -0.2477

Max Act: 0.1667. Min Act: -0.0003

Data Index: 259777 (C4 (Web Text))

Max Activating Token Index: 738

Text #19

Max Range: 0.2477. Min Range: -0.2477

Max Act: 0.1620. Min Act: -0.0003

Data Index: 710985 (C4 (Web Text))

Max Activating Token Index: 49