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

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

Neuron 2872 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: 1.1175. Min Range: -1.1175

Max Act: 1.0998. Min Act: -0.0000

Data Index: 787164 (C4 (Web Text))

Max Activating Token Index: 600

Text #1

Max Range: 1.1175. Min Range: -1.1175

Max Act: 1.0830. Min Act: -0.0000

Data Index: 1277728 (C4 (Web Text))

Max Activating Token Index: 916

Text #2

Max Range: 1.1175. Min Range: -1.1175

Max Act: 0.9972. Min Act: -0.0000

Data Index: 943996 (C4 (Web Text))

Max Activating Token Index: 829

Text #3

Max Range: 1.1175. Min Range: -1.1175

Max Act: 1.0392. Min Act: -0.0000

Data Index: 350906 (C4 (Web Text))

Max Activating Token Index: 563

Text #4

Max Range: 1.1175. Min Range: -1.1175

Max Act: 1.0756. Min Act: -0.0000

Data Index: 728345 (C4 (Web Text))

Max Activating Token Index: 678

Text #5

Max Range: 1.1175. Min Range: -1.1175

Max Act: 1.1175. Min Act: -0.0000

Data Index: 638008 (C4 (Web Text))

Max Activating Token Index: 825

Text #6

Max Range: 1.1175. Min Range: -1.1175

Max Act: 0.9802. Min Act: -0.0000

Data Index: 549734 (C4 (Web Text))

Max Activating Token Index: 637

Text #7

Max Range: 1.1175. Min Range: -1.1175

Max Act: 0.9289. Min Act: -0.0000

Data Index: 940041 (C4 (Web Text))

Max Activating Token Index: 938

Text #8

Max Range: 1.1175. Min Range: -1.1175

Max Act: 0.9348. Min Act: -0.0000

Data Index: 411698 (C4 (Web Text))

Max Activating Token Index: 616

Text #9

Max Range: 1.1175. Min Range: -1.1175

Max Act: 0.8691. Min Act: -0.0000

Data Index: 279365 (C4 (Web Text))

Max Activating Token Index: 403

Text #10

Max Range: 1.1175. Min Range: -1.1175

Max Act: 0.8891. Min Act: -0.0000

Data Index: 1356320 (C4 (Web Text))

Max Activating Token Index: 448

Text #11

Max Range: 1.1175. Min Range: -1.1175

Max Act: 0.8487. Min Act: -0.0000

Data Index: 1298323 (C4 (Web Text))

Max Activating Token Index: 971

Text #12

Max Range: 1.1175. Min Range: -1.1175

Max Act: 0.8771. Min Act: -0.0000

Data Index: 315602 (C4 (Web Text))

Max Activating Token Index: 973

Text #13

Max Range: 1.1175. Min Range: -1.1175

Max Act: 0.9234. Min Act: -0.0000

Data Index: 369317 (C4 (Web Text))

Max Activating Token Index: 625

Text #14

Max Range: 1.1175. Min Range: -1.1175

Max Act: 0.8258. Min Act: -0.0000

Data Index: 911456 (C4 (Web Text))

Max Activating Token Index: 772

Text #15

Max Range: 1.1175. Min Range: -1.1175

Max Act: 0.8220. Min Act: -0.0000

Data Index: 614471 (C4 (Web Text))

Max Activating Token Index: 581

Text #16

Max Range: 1.1175. Min Range: -1.1175

Max Act: 0.8190. Min Act: -0.0000

Data Index: 718058 (C4 (Web Text))

Max Activating Token Index: 569

Text #17

Max Range: 1.1175. Min Range: -1.1175

Max Act: 0.8664. Min Act: -0.0000

Data Index: 127249 (C4 (Web Text))

Max Activating Token Index: 980

Text #18

Max Range: 1.1175. Min Range: -1.1175

Max Act: 0.8657. Min Act: -0.0000

Data Index: 1313832 (C4 (Web Text))

Max Activating Token Index: 192

Text #19

Max Range: 1.1175. Min Range: -1.1175

Max Act: 0.9616. Min Act: -0.0000

Data Index: 168622 (C4 (Web Text))

Max Activating Token Index: 975