Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 15 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.6425. Min Range: -2.6425

Max Act: 2.6425. Min Act: -0.0000

Data Index: 5 (C4 (Web Text))

Max Activating Token Index: 198

Text #1

Max Range: 2.6425. Min Range: -2.6425

Max Act: 2.4062. Min Act: -0.0000

Data Index: 1018953 (C4 (Web Text))

Max Activating Token Index: 164

Text #2

Max Range: 2.6425. Min Range: -2.6425

Max Act: 1.5024. Min Act: -0.0000

Data Index: 763018 (C4 (Web Text))

Max Activating Token Index: 1021

Text #3

Max Range: 2.6425. Min Range: -2.6425

Max Act: 1.4155. Min Act: -0.0000

Data Index: 1039098 (C4 (Web Text))

Max Activating Token Index: 290

Text #4

Max Range: 2.6425. Min Range: -2.6425

Max Act: 1.3076. Min Act: -0.0000

Data Index: 438270 (C4 (Web Text))

Max Activating Token Index: 649

Text #5

Max Range: 2.6425. Min Range: -2.6425

Max Act: 1.2991. Min Act: -0.0000

Data Index: 814591 (C4 (Web Text))

Max Activating Token Index: 983

Text #6

Max Range: 2.6425. Min Range: -2.6425

Max Act: 1.2221. Min Act: -0.0000

Data Index: 1252262 (C4 (Web Text))

Max Activating Token Index: 215

Text #7

Max Range: 2.6425. Min Range: -2.6425

Max Act: 1.2849. Min Act: -0.0000

Data Index: 350265 (C4 (Web Text))

Max Activating Token Index: 982

Text #8

Max Range: 2.6425. Min Range: -2.6425

Max Act: 1.1809. Min Act: -0.0000

Data Index: 934051 (C4 (Web Text))

Max Activating Token Index: 267

Text #9

Max Range: 2.6425. Min Range: -2.6425

Max Act: 1.1994. Min Act: -0.0000

Data Index: 124397 (C4 (Web Text))

Max Activating Token Index: 71

Text #10

Max Range: 2.6425. Min Range: -2.6425

Max Act: 1.2302. Min Act: -0.0000

Data Index: 988843 (C4 (Web Text))

Max Activating Token Index: 440

Text #11

Max Range: 2.6425. Min Range: -2.6425

Max Act: 1.1801. Min Act: -0.0000

Data Index: 1043784 (C4 (Web Text))

Max Activating Token Index: 54

Text #12

Max Range: 2.6425. Min Range: -2.6425

Max Act: 1.1442. Min Act: -0.0000

Data Index: 616519 (C4 (Web Text))

Max Activating Token Index: 969

Text #13

Max Range: 2.6425. Min Range: -2.6425

Max Act: 1.2444. Min Act: -0.0000

Data Index: 1247080 (C4 (Web Text))

Max Activating Token Index: 123

Text #14

Max Range: 2.6425. Min Range: -2.6425

Max Act: 1.1999. Min Act: -0.0000

Data Index: 511964 (C4 (Web Text))

Max Activating Token Index: 162

Text #15

Max Range: 2.6425. Min Range: -2.6425

Max Act: 1.2262. Min Act: -0.0000

Data Index: 144602 (C4 (Web Text))

Max Activating Token Index: 820

Text #16

Max Range: 2.6425. Min Range: -2.6425

Max Act: 1.2686. Min Act: -0.0000

Data Index: 961517 (C4 (Web Text))

Max Activating Token Index: 314

Text #17

Max Range: 2.6425. Min Range: -2.6425

Max Act: 1.1972. Min Act: -0.0000

Data Index: 433582 (C4 (Web Text))

Max Activating Token Index: 870

Text #18

Max Range: 2.6425. Min Range: -2.6425

Max Act: 1.0949. Min Act: -0.0000

Data Index: 1281751 (C4 (Web Text))

Max Activating Token Index: 348

Text #19

Max Range: 2.6425. Min Range: -2.6425

Max Act: 1.1941. Min Act: -0.0000

Data Index: 989431 (C4 (Web Text))

Max Activating Token Index: 990