Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 96 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.9481. Min Range: -0.9481

Max Act: 0.8811. Min Act: -0.0003

Data Index: 612682 (C4 (Web Text))

Max Activating Token Index: 553

Text #1

Max Range: 0.9481. Min Range: -0.9481

Max Act: 0.6015. Min Act: -0.0003

Data Index: 56406 (C4 (Web Text))

Max Activating Token Index: 304

Text #2

Max Range: 0.9481. Min Range: -0.9481

Max Act: 0.8393. Min Act: -0.0003

Data Index: 66900 (C4 (Web Text))

Max Activating Token Index: 507

Text #3

Max Range: 0.9481. Min Range: -0.9481

Max Act: 0.8312. Min Act: -0.0003

Data Index: 547511 (C4 (Web Text))

Max Activating Token Index: 709

Text #4

Max Range: 0.9481. Min Range: -0.9481

Max Act: 0.7005. Min Act: -0.0003

Data Index: 412014 (C4 (Web Text))

Max Activating Token Index: 574

Text #5

Max Range: 0.9481. Min Range: -0.9481

Max Act: 0.9414. Min Act: -0.0003

Data Index: 692239 (C4 (Web Text))

Max Activating Token Index: 905

Text #6

Max Range: 0.9481. Min Range: -0.9481

Max Act: 0.7111. Min Act: -0.0003

Data Index: 1313712 (C4 (Web Text))

Max Activating Token Index: 728

Text #7

Max Range: 0.9481. Min Range: -0.9481

Max Act: 0.8554. Min Act: -0.0003

Data Index: 73648 (C4 (Web Text))

Max Activating Token Index: 303

Text #8

Max Range: 0.9481. Min Range: -0.9481

Max Act: 0.8211. Min Act: -0.0003

Data Index: 1336699 (C4 (Web Text))

Max Activating Token Index: 456

Text #9

Max Range: 0.9481. Min Range: -0.9481

Max Act: 0.9481. Min Act: -0.0003

Data Index: 131577 (C4 (Web Text))

Max Activating Token Index: 977

Text #10

Max Range: 0.9481. Min Range: -0.9481

Max Act: 0.5385. Min Act: -0.0003

Data Index: 653145 (C4 (Web Text))

Max Activating Token Index: 577

Text #11

Max Range: 0.9481. Min Range: -0.9481

Max Act: 0.7817. Min Act: -0.0003

Data Index: 287823 (C4 (Web Text))

Max Activating Token Index: 339

Text #12

Max Range: 0.9481. Min Range: -0.9481

Max Act: 0.8027. Min Act: -0.0003

Data Index: 253267 (C4 (Web Text))

Max Activating Token Index: 403

Text #13

Max Range: 0.9481. Min Range: -0.9481

Max Act: 0.6893. Min Act: -0.0003

Data Index: 60468 (C4 (Web Text))

Max Activating Token Index: 872

Text #14

Max Range: 0.9481. Min Range: -0.9481

Max Act: 0.7035. Min Act: -0.0003

Data Index: 376645 (C4 (Web Text))

Max Activating Token Index: 578

Text #15

Max Range: 0.9481. Min Range: -0.9481

Max Act: 0.6592. Min Act: -0.0003

Data Index: 1289221 (C4 (Web Text))

Max Activating Token Index: 737

Text #16

Max Range: 0.9481. Min Range: -0.9481

Max Act: 0.7432. Min Act: -0.0003

Data Index: 989865 (C4 (Web Text))

Max Activating Token Index: 348

Text #17

Max Range: 0.9481. Min Range: -0.9481

Max Act: 0.6187. Min Act: -0.0003

Data Index: 696749 (C4 (Web Text))

Max Activating Token Index: 632

Text #18

Max Range: 0.9481. Min Range: -0.9481

Max Act: 0.7240. Min Act: -0.0003

Data Index: 913984 (C4 (Web Text))

Max Activating Token Index: 772

Text #19

Max Range: 0.9481. Min Range: -0.9481

Max Act: 0.7230. Min Act: -0.0003

Data Index: 668331 (C4 (Web Text))

Max Activating Token Index: 725