Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3331 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0477. Min Act: -0.0003

Data Index: 319625 (C4 (Web Text))

Max Activating Token Index: 660

Text #1

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0432. Min Act: -0.0003

Data Index: 1387318 (Python Code)

Max Activating Token Index: 751

Text #2

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0444. Min Act: -0.0003

Data Index: 1408990 (Python Code)

Max Activating Token Index: 872

Text #3

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0454. Min Act: -0.0003

Data Index: 434915 (C4 (Web Text))

Max Activating Token Index: 396

Text #4

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0433. Min Act: -0.0003

Data Index: 1512924 (Python Code)

Max Activating Token Index: 739

Text #5

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0386. Min Act: -0.0003

Data Index: 1056042 (C4 (Web Text))

Max Activating Token Index: 936

Text #6

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0438. Min Act: -0.0003

Data Index: 15207 (C4 (Web Text))

Max Activating Token Index: 196

Text #7

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0392. Min Act: -0.0003

Data Index: 652796 (C4 (Web Text))

Max Activating Token Index: 980

Text #8

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0486. Min Act: -0.0003

Data Index: 897450 (C4 (Web Text))

Max Activating Token Index: 741

Text #9

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0407. Min Act: -0.0003

Data Index: 1549964 (Python Code)

Max Activating Token Index: 1005

Text #10

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0402. Min Act: -0.0003

Data Index: 1134252 (C4 (Web Text))

Max Activating Token Index: 762

Text #11

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0417. Min Act: -0.0003

Data Index: 402535 (C4 (Web Text))

Max Activating Token Index: 626

Text #12

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0434. Min Act: -0.0003

Data Index: 866389 (C4 (Web Text))

Max Activating Token Index: 549

Text #13

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0427. Min Act: -0.0003

Data Index: 744111 (C4 (Web Text))

Max Activating Token Index: 396

Text #14

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0374. Min Act: -0.0003

Data Index: 620874 (C4 (Web Text))

Max Activating Token Index: 351

Text #15

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0374. Min Act: -0.0003

Data Index: 558801 (C4 (Web Text))

Max Activating Token Index: 984

Text #16

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0406. Min Act: -0.0003

Data Index: 198104 (C4 (Web Text))

Max Activating Token Index: 657

Text #17

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0425. Min Act: -0.0003

Data Index: 257034 (C4 (Web Text))

Max Activating Token Index: 576

Text #18

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0388. Min Act: -0.0003

Data Index: 1565470 (Python Code)

Max Activating Token Index: 684

Text #19

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0368. Min Act: -0.0003

Data Index: 1373494 (Python Code)

Max Activating Token Index: 895