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

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

Neuron 2364 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2661. Min Range: -0.2661

Max Act: 0.2661. Min Act: -0.0001

Data Index: 664719 (C4 (Web Text))

Max Activating Token Index: 840

Text #1

Max Range: 0.2661. Min Range: -0.2661

Max Act: 0.2389. Min Act: -0.0001

Data Index: 1350551 (C4 (Web Text))

Max Activating Token Index: 193

Text #2

Max Range: 0.2661. Min Range: -0.2661

Max Act: 0.2526. Min Act: -0.0001

Data Index: 1301041 (C4 (Web Text))

Max Activating Token Index: 494

Text #3

Max Range: 0.2661. Min Range: -0.2661

Max Act: 0.2408. Min Act: -0.0000

Data Index: 993242 (C4 (Web Text))

Max Activating Token Index: 375

Text #4

Max Range: 0.2661. Min Range: -0.2661

Max Act: 0.2336. Min Act: -0.0001

Data Index: 1017389 (C4 (Web Text))

Max Activating Token Index: 240

Text #5

Max Range: 0.2661. Min Range: -0.2661

Max Act: 0.2245. Min Act: -0.0001

Data Index: 37486 (C4 (Web Text))

Max Activating Token Index: 306

Text #6

Max Range: 0.2661. Min Range: -0.2661

Max Act: 0.2245. Min Act: -0.0001

Data Index: 1105447 (C4 (Web Text))

Max Activating Token Index: 322

Text #7

Max Range: 0.2661. Min Range: -0.2661

Max Act: 0.2103. Min Act: -0.0001

Data Index: 1281955 (C4 (Web Text))

Max Activating Token Index: 692

Text #8

Max Range: 0.2661. Min Range: -0.2661

Max Act: 0.2171. Min Act: -0.0000

Data Index: 1066664 (C4 (Web Text))

Max Activating Token Index: 267

Text #9

Max Range: 0.2661. Min Range: -0.2661

Max Act: 0.2145. Min Act: -0.0000

Data Index: 812506 (C4 (Web Text))

Max Activating Token Index: 20

Text #10

Max Range: 0.2661. Min Range: -0.2661

Max Act: 0.2149. Min Act: -0.0000

Data Index: 893674 (C4 (Web Text))

Max Activating Token Index: 344

Text #11

Max Range: 0.2661. Min Range: -0.2661

Max Act: 0.2039. Min Act: -0.0001

Data Index: 594398 (C4 (Web Text))

Max Activating Token Index: 808

Text #12

Max Range: 0.2661. Min Range: -0.2661

Max Act: 0.2081. Min Act: -0.0001

Data Index: 1280821 (C4 (Web Text))

Max Activating Token Index: 949

Text #13

Max Range: 0.2661. Min Range: -0.2661

Max Act: 0.2072. Min Act: -0.0000

Data Index: 398197 (C4 (Web Text))

Max Activating Token Index: 808

Text #14

Max Range: 0.2661. Min Range: -0.2661

Max Act: 0.1966. Min Act: -0.0000

Data Index: 1047571 (C4 (Web Text))

Max Activating Token Index: 907

Text #15

Max Range: 0.2661. Min Range: -0.2661

Max Act: 0.2270. Min Act: -0.0000

Data Index: 1037690 (C4 (Web Text))

Max Activating Token Index: 817

Text #16

Max Range: 0.2661. Min Range: -0.2661

Max Act: 0.2216. Min Act: -0.0001

Data Index: 1102621 (C4 (Web Text))

Max Activating Token Index: 394

Text #17

Max Range: 0.2661. Min Range: -0.2661

Max Act: 0.2045. Min Act: -0.0000

Data Index: 376146 (C4 (Web Text))

Max Activating Token Index: 166

Text #18

Max Range: 0.2661. Min Range: -0.2661

Max Act: 0.1996. Min Act: -0.0001

Data Index: 282014 (C4 (Web Text))

Max Activating Token Index: 938

Text #19

Max Range: 0.2661. Min Range: -0.2661

Max Act: 0.1948. Min Act: -0.0000

Data Index: 352093 (C4 (Web Text))

Max Activating Token Index: 691