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

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

Neuron 1973 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: 0.2536. Min Range: -0.2536

Max Act: 0.2536. Min Act: -0.0003

Data Index: 332196 (C4 (Web Text))

Max Activating Token Index: 1014

Text #1

Max Range: 0.2536. Min Range: -0.2536

Max Act: 0.2442. Min Act: -0.0003

Data Index: 492075 (C4 (Web Text))

Max Activating Token Index: 642

Text #2

Max Range: 0.2536. Min Range: -0.2536

Max Act: 0.2433. Min Act: -0.0003

Data Index: 604911 (C4 (Web Text))

Max Activating Token Index: 429

Text #3

Max Range: 0.2536. Min Range: -0.2536

Max Act: 0.2091. Min Act: -0.0003

Data Index: 549219 (C4 (Web Text))

Max Activating Token Index: 561

Text #4

Max Range: 0.2536. Min Range: -0.2536

Max Act: 0.2204. Min Act: -0.0003

Data Index: 1155130 (C4 (Web Text))

Max Activating Token Index: 534

Text #5

Max Range: 0.2536. Min Range: -0.2536

Max Act: 0.2178. Min Act: -0.0003

Data Index: 585496 (C4 (Web Text))

Max Activating Token Index: 111

Text #6

Max Range: 0.2536. Min Range: -0.2536

Max Act: 0.2183. Min Act: -0.0003

Data Index: 441237 (C4 (Web Text))

Max Activating Token Index: 1000

Text #7

Max Range: 0.2536. Min Range: -0.2536

Max Act: 0.2150. Min Act: -0.0003

Data Index: 234345 (C4 (Web Text))

Max Activating Token Index: 749

Text #8

Max Range: 0.2536. Min Range: -0.2536

Max Act: 0.1988. Min Act: -0.0003

Data Index: 73194 (C4 (Web Text))

Max Activating Token Index: 376

Text #9

Max Range: 0.2536. Min Range: -0.2536

Max Act: 0.2146. Min Act: -0.0003

Data Index: 1250954 (C4 (Web Text))

Max Activating Token Index: 332

Text #10

Max Range: 0.2536. Min Range: -0.2536

Max Act: 0.2037. Min Act: -0.0003

Data Index: 386689 (C4 (Web Text))

Max Activating Token Index: 585

Text #11

Max Range: 0.2536. Min Range: -0.2536

Max Act: 0.2052. Min Act: -0.0003

Data Index: 748413 (C4 (Web Text))

Max Activating Token Index: 430

Text #12

Max Range: 0.2536. Min Range: -0.2536

Max Act: 0.2145. Min Act: -0.0003

Data Index: 1248056 (C4 (Web Text))

Max Activating Token Index: 221

Text #13

Max Range: 0.2536. Min Range: -0.2536

Max Act: 0.2038. Min Act: -0.0003

Data Index: 536431 (C4 (Web Text))

Max Activating Token Index: 942

Text #14

Max Range: 0.2536. Min Range: -0.2536

Max Act: 0.2094. Min Act: -0.0003

Data Index: 1145098 (C4 (Web Text))

Max Activating Token Index: 978

Text #15

Max Range: 0.2536. Min Range: -0.2536

Max Act: 0.2160. Min Act: -0.0003

Data Index: 682969 (C4 (Web Text))

Max Activating Token Index: 87

Text #16

Max Range: 0.2536. Min Range: -0.2536

Max Act: 0.1999. Min Act: -0.0003

Data Index: 390738 (C4 (Web Text))

Max Activating Token Index: 913

Text #17

Max Range: 0.2536. Min Range: -0.2536

Max Act: 0.1955. Min Act: -0.0003

Data Index: 708452 (C4 (Web Text))

Max Activating Token Index: 313

Text #18

Max Range: 0.2536. Min Range: -0.2536

Max Act: 0.2049. Min Act: -0.0003

Data Index: 273697 (C4 (Web Text))

Max Activating Token Index: 397

Text #19

Max Range: 0.2536. Min Range: -0.2536

Max Act: 0.2207. Min Act: -0.0003

Data Index: 864878 (C4 (Web Text))

Max Activating Token Index: 950