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

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

Neuron 3776 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3302. Min Range: -0.3302

Max Act: 0.3302. Min Act: -0.0000

Data Index: 1022261 (C4 (Web Text))

Max Activating Token Index: 686

Text #1

Max Range: 0.3302. Min Range: -0.3302

Max Act: 0.2504. Min Act: -0.0000

Data Index: 1192518 (C4 (Web Text))

Max Activating Token Index: 805

Text #2

Max Range: 0.3302. Min Range: -0.3302

Max Act: 0.2356. Min Act: -0.0000

Data Index: 1143215 (C4 (Web Text))

Max Activating Token Index: 699

Text #3

Max Range: 0.3302. Min Range: -0.3302

Max Act: 0.2506. Min Act: -0.0000

Data Index: 623974 (C4 (Web Text))

Max Activating Token Index: 405

Text #4

Max Range: 0.3302. Min Range: -0.3302

Max Act: 0.2192. Min Act: -0.0000

Data Index: 973553 (C4 (Web Text))

Max Activating Token Index: 372

Text #5

Max Range: 0.3302. Min Range: -0.3302

Max Act: 0.2214. Min Act: -0.0000

Data Index: 1600811 (Python Code)

Max Activating Token Index: 408

Text #6

Max Range: 0.3302. Min Range: -0.3302

Max Act: 0.2205. Min Act: -0.0000

Data Index: 964812 (C4 (Web Text))

Max Activating Token Index: 882

Text #7

Max Range: 0.3302. Min Range: -0.3302

Max Act: 0.2237. Min Act: -0.0000

Data Index: 636006 (C4 (Web Text))

Max Activating Token Index: 531

Text #8

Max Range: 0.3302. Min Range: -0.3302

Max Act: 0.2105. Min Act: -0.0000

Data Index: 1321097 (C4 (Web Text))

Max Activating Token Index: 979

Text #9

Max Range: 0.3302. Min Range: -0.3302

Max Act: 0.2110. Min Act: -0.0000

Data Index: 820203 (C4 (Web Text))

Max Activating Token Index: 73

Text #10

Max Range: 0.3302. Min Range: -0.3302

Max Act: 0.2088. Min Act: -0.0000

Data Index: 795057 (C4 (Web Text))

Max Activating Token Index: 889

Text #11

Max Range: 0.3302. Min Range: -0.3302

Max Act: 0.2038. Min Act: -0.0000

Data Index: 58259 (C4 (Web Text))

Max Activating Token Index: 450

Text #12

Max Range: 0.3302. Min Range: -0.3302

Max Act: 0.2010. Min Act: -0.0000

Data Index: 1446996 (Python Code)

Max Activating Token Index: 701

Text #13

Max Range: 0.3302. Min Range: -0.3302

Max Act: 0.2024. Min Act: -0.0000

Data Index: 386030 (C4 (Web Text))

Max Activating Token Index: 462

Text #14

Max Range: 0.3302. Min Range: -0.3302

Max Act: 0.1804. Min Act: -0.0000

Data Index: 1486410 (Python Code)

Max Activating Token Index: 246

Text #15

Max Range: 0.3302. Min Range: -0.3302

Max Act: 0.1897. Min Act: -0.0000

Data Index: 874200 (C4 (Web Text))

Max Activating Token Index: 460

Text #16

Max Range: 0.3302. Min Range: -0.3302

Max Act: 0.1927. Min Act: -0.0000

Data Index: 852469 (C4 (Web Text))

Max Activating Token Index: 634

Text #17

Max Range: 0.3302. Min Range: -0.3302

Max Act: 0.1967. Min Act: -0.0000

Data Index: 613742 (C4 (Web Text))

Max Activating Token Index: 659

Text #18

Max Range: 0.3302. Min Range: -0.3302

Max Act: 0.2002. Min Act: -0.0000

Data Index: 1475739 (Python Code)

Max Activating Token Index: 814

Text #19

Max Range: 0.3302. Min Range: -0.3302

Max Act: 0.1961. Min Act: -0.0000

Data Index: 769054 (C4 (Web Text))

Max Activating Token Index: 343