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

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

Neuron 1091 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.3461. Min Range: -4.3461

Max Act: 4.3461. Min Act: -0.0000

Data Index: 1619114 (Python Code)

Max Activating Token Index: 950

Text #1

Max Range: 4.3461. Min Range: -4.3461

Max Act: 4.0422. Min Act: -0.0000

Data Index: 352005 (C4 (Web Text))

Max Activating Token Index: 37

Text #2

Max Range: 4.3461. Min Range: -4.3461

Max Act: 3.3297. Min Act: -0.0000

Data Index: 955890 (C4 (Web Text))

Max Activating Token Index: 92

Text #3

Max Range: 4.3461. Min Range: -4.3461

Max Act: 3.3486. Min Act: -0.0000

Data Index: 39397 (C4 (Web Text))

Max Activating Token Index: 985

Text #4

Max Range: 4.3461. Min Range: -4.3461

Max Act: 3.0096. Min Act: -0.0000

Data Index: 632295 (C4 (Web Text))

Max Activating Token Index: 769

Text #5

Max Range: 4.3461. Min Range: -4.3461

Max Act: 3.1352. Min Act: -0.0000

Data Index: 955868 (C4 (Web Text))

Max Activating Token Index: 773

Text #6

Max Range: 4.3461. Min Range: -4.3461

Max Act: 3.0655. Min Act: -0.0000

Data Index: 1328543 (C4 (Web Text))

Max Activating Token Index: 591

Text #7

Max Range: 4.3461. Min Range: -4.3461

Max Act: 3.1543. Min Act: -0.0000

Data Index: 230031 (C4 (Web Text))

Max Activating Token Index: 914

Text #8

Max Range: 4.3461. Min Range: -4.3461

Max Act: 2.8513. Min Act: -0.0000

Data Index: 120954 (C4 (Web Text))

Max Activating Token Index: 479

Text #9

Max Range: 4.3461. Min Range: -4.3461

Max Act: 2.9935. Min Act: -0.0000

Data Index: 1205858 (C4 (Web Text))

Max Activating Token Index: 828

Text #10

Max Range: 4.3461. Min Range: -4.3461

Max Act: 2.8198. Min Act: -0.0000

Data Index: 679221 (C4 (Web Text))

Max Activating Token Index: 900

Text #11

Max Range: 4.3461. Min Range: -4.3461

Max Act: 2.9272. Min Act: -0.0000

Data Index: 1084798 (C4 (Web Text))

Max Activating Token Index: 687

Text #12

Max Range: 4.3461. Min Range: -4.3461

Max Act: 2.8035. Min Act: -0.0000

Data Index: 283424 (C4 (Web Text))

Max Activating Token Index: 740

Text #13

Max Range: 4.3461. Min Range: -4.3461

Max Act: 2.6183. Min Act: -0.0000

Data Index: 602081 (C4 (Web Text))

Max Activating Token Index: 684

Text #14

Max Range: 4.3461. Min Range: -4.3461

Max Act: 3.0506. Min Act: -0.0000

Data Index: 612734 (C4 (Web Text))

Max Activating Token Index: 676

Text #15

Max Range: 4.3461. Min Range: -4.3461

Max Act: 2.8955. Min Act: -0.0000

Data Index: 86810 (C4 (Web Text))

Max Activating Token Index: 555

Text #16

Max Range: 4.3461. Min Range: -4.3461

Max Act: 3.0066. Min Act: -0.0000

Data Index: 858104 (C4 (Web Text))

Max Activating Token Index: 269

Text #17

Max Range: 4.3461. Min Range: -4.3461

Max Act: 2.8578. Min Act: -0.0000

Data Index: 958465 (C4 (Web Text))

Max Activating Token Index: 576

Text #18

Max Range: 4.3461. Min Range: -4.3461

Max Act: 2.8356. Min Act: -0.0000

Data Index: 454438 (C4 (Web Text))

Max Activating Token Index: 655

Text #19

Max Range: 4.3461. Min Range: -4.3461

Max Act: 2.8112. Min Act: -0.0000

Data Index: 292343 (C4 (Web Text))

Max Activating Token Index: 551