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

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

Neuron 2841 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3478. Min Range: -0.3478

Max Act: 0.3478. Min Act: -0.0000

Data Index: 315354 (C4 (Web Text))

Max Activating Token Index: 228

Text #1

Max Range: 0.3478. Min Range: -0.3478

Max Act: 0.2693. Min Act: -0.0000

Data Index: 1218003 (C4 (Web Text))

Max Activating Token Index: 690

Text #2

Max Range: 0.3478. Min Range: -0.3478

Max Act: 0.2760. Min Act: -0.0000

Data Index: 301398 (C4 (Web Text))

Max Activating Token Index: 656

Text #3

Max Range: 0.3478. Min Range: -0.3478

Max Act: 0.2506. Min Act: -0.0000

Data Index: 1033958 (C4 (Web Text))

Max Activating Token Index: 885

Text #4

Max Range: 0.3478. Min Range: -0.3478

Max Act: 0.2430. Min Act: -0.0000

Data Index: 591853 (C4 (Web Text))

Max Activating Token Index: 929

Text #5

Max Range: 0.3478. Min Range: -0.3478

Max Act: 0.2222. Min Act: -0.0000

Data Index: 216022 (C4 (Web Text))

Max Activating Token Index: 676

Text #6

Max Range: 0.3478. Min Range: -0.3478

Max Act: 0.2139. Min Act: -0.0000

Data Index: 878997 (C4 (Web Text))

Max Activating Token Index: 464

Text #7

Max Range: 0.3478. Min Range: -0.3478

Max Act: 0.2033. Min Act: -0.0000

Data Index: 818914 (C4 (Web Text))

Max Activating Token Index: 390

Text #8

Max Range: 0.3478. Min Range: -0.3478

Max Act: 0.2069. Min Act: -0.0000

Data Index: 941968 (C4 (Web Text))

Max Activating Token Index: 367

Text #9

Max Range: 0.3478. Min Range: -0.3478

Max Act: 0.1981. Min Act: -0.0000

Data Index: 708010 (C4 (Web Text))

Max Activating Token Index: 691

Text #10

Max Range: 0.3478. Min Range: -0.3478

Max Act: 0.1927. Min Act: -0.0000

Data Index: 926411 (C4 (Web Text))

Max Activating Token Index: 447

Text #11

Max Range: 0.3478. Min Range: -0.3478

Max Act: 0.1965. Min Act: -0.0000

Data Index: 212617 (C4 (Web Text))

Max Activating Token Index: 962

Text #12

Max Range: 0.3478. Min Range: -0.3478

Max Act: 0.1903. Min Act: -0.0000

Data Index: 609553 (C4 (Web Text))

Max Activating Token Index: 503

Text #13

Max Range: 0.3478. Min Range: -0.3478

Max Act: 0.1962. Min Act: -0.0000

Data Index: 248051 (C4 (Web Text))

Max Activating Token Index: 345

Text #14

Max Range: 0.3478. Min Range: -0.3478

Max Act: 0.1864. Min Act: -0.0000

Data Index: 1144244 (C4 (Web Text))

Max Activating Token Index: 643

Text #15

Max Range: 0.3478. Min Range: -0.3478

Max Act: 0.1816. Min Act: -0.0000

Data Index: 911427 (C4 (Web Text))

Max Activating Token Index: 84

Text #16

Max Range: 0.3478. Min Range: -0.3478

Max Act: 0.1846. Min Act: -0.0000

Data Index: 434778 (C4 (Web Text))

Max Activating Token Index: 429

Text #17

Max Range: 0.3478. Min Range: -0.3478

Max Act: 0.1720. Min Act: -0.0000

Data Index: 120389 (C4 (Web Text))

Max Activating Token Index: 878

Text #18

Max Range: 0.3478. Min Range: -0.3478

Max Act: 0.1960. Min Act: -0.0000

Data Index: 1084842 (C4 (Web Text))

Max Activating Token Index: 789

Text #19

Max Range: 0.3478. Min Range: -0.3478

Max Act: 0.1799. Min Act: -0.0000

Data Index: 619735 (C4 (Web Text))

Max Activating Token Index: 972