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

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

Neuron 4370 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5870. Min Range: -3.5870

Max Act: 3.5870. Min Act: -0.0000

Data Index: 413423 (C4 (Web Text))

Max Activating Token Index: 643

Text #1

Max Range: 3.5870. Min Range: -3.5870

Max Act: 3.4581. Min Act: -0.0000

Data Index: 569663 (C4 (Web Text))

Max Activating Token Index: 390

Text #2

Max Range: 3.5870. Min Range: -3.5870

Max Act: 2.9820. Min Act: -0.0000

Data Index: 635892 (C4 (Web Text))

Max Activating Token Index: 653

Text #3

Max Range: 3.5870. Min Range: -3.5870

Max Act: 2.9535. Min Act: -0.0000

Data Index: 184495 (C4 (Web Text))

Max Activating Token Index: 977

Text #4

Max Range: 3.5870. Min Range: -3.5870

Max Act: 3.0302. Min Act: -0.0000

Data Index: 952258 (C4 (Web Text))

Max Activating Token Index: 85

Text #5

Max Range: 3.5870. Min Range: -3.5870

Max Act: 2.7910. Min Act: -0.0000

Data Index: 1293785 (C4 (Web Text))

Max Activating Token Index: 436

Text #6

Max Range: 3.5870. Min Range: -3.5870

Max Act: 2.7539. Min Act: -0.0000

Data Index: 246270 (C4 (Web Text))

Max Activating Token Index: 987

Text #7

Max Range: 3.5870. Min Range: -3.5870

Max Act: 2.8442. Min Act: -0.0000

Data Index: 510405 (C4 (Web Text))

Max Activating Token Index: 708

Text #8

Max Range: 3.5870. Min Range: -3.5870

Max Act: 2.6772. Min Act: -0.0000

Data Index: 215670 (C4 (Web Text))

Max Activating Token Index: 979

Text #9

Max Range: 3.5870. Min Range: -3.5870

Max Act: 2.6720. Min Act: -0.0000

Data Index: 424706 (C4 (Web Text))

Max Activating Token Index: 804

Text #10

Max Range: 3.5870. Min Range: -3.5870

Max Act: 2.5275. Min Act: -0.0000

Data Index: 20723 (C4 (Web Text))

Max Activating Token Index: 688

Text #11

Max Range: 3.5870. Min Range: -3.5870

Max Act: 2.1834. Min Act: -0.0000

Data Index: 278685 (C4 (Web Text))

Max Activating Token Index: 743

Text #12

Max Range: 3.5870. Min Range: -3.5870

Max Act: 2.3727. Min Act: -0.0000

Data Index: 14928 (C4 (Web Text))

Max Activating Token Index: 431

Text #13

Max Range: 3.5870. Min Range: -3.5870

Max Act: 2.4856. Min Act: -0.0000

Data Index: 72398 (C4 (Web Text))

Max Activating Token Index: 953

Text #14

Max Range: 3.5870. Min Range: -3.5870

Max Act: 2.3243. Min Act: -0.0000

Data Index: 180714 (C4 (Web Text))

Max Activating Token Index: 216

Text #15

Max Range: 3.5870. Min Range: -3.5870

Max Act: 2.2599. Min Act: -0.0000

Data Index: 743709 (C4 (Web Text))

Max Activating Token Index: 415

Text #16

Max Range: 3.5870. Min Range: -3.5870

Max Act: 2.1564. Min Act: -0.0000

Data Index: 141322 (C4 (Web Text))

Max Activating Token Index: 768

Text #17

Max Range: 3.5870. Min Range: -3.5870

Max Act: 2.2584. Min Act: -0.0000

Data Index: 502576 (C4 (Web Text))

Max Activating Token Index: 637

Text #18

Max Range: 3.5870. Min Range: -3.5870

Max Act: 2.3354. Min Act: -0.0000

Data Index: 1325567 (C4 (Web Text))

Max Activating Token Index: 437

Text #19

Max Range: 3.5870. Min Range: -3.5870

Max Act: 2.2926. Min Act: -0.0000

Data Index: 1166537 (C4 (Web Text))

Max Activating Token Index: 359