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

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

Neuron 5828 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: 0.3364. Min Range: -0.3364

Max Act: 0.3364. Min Act: -0.0000

Data Index: 229158 (C4 (Web Text))

Max Activating Token Index: 660

Text #1

Max Range: 0.3364. Min Range: -0.3364

Max Act: 0.3031. Min Act: -0.0000

Data Index: 120154 (C4 (Web Text))

Max Activating Token Index: 444

Text #2

Max Range: 0.3364. Min Range: -0.3364

Max Act: 0.3038. Min Act: -0.0000

Data Index: 1576955 (Python Code)

Max Activating Token Index: 153

Text #3

Max Range: 0.3364. Min Range: -0.3364

Max Act: 0.2874. Min Act: -0.0000

Data Index: 608076 (C4 (Web Text))

Max Activating Token Index: 210

Text #4

Max Range: 0.3364. Min Range: -0.3364

Max Act: 0.2585. Min Act: -0.0000

Data Index: 662580 (C4 (Web Text))

Max Activating Token Index: 959

Text #5

Max Range: 0.3364. Min Range: -0.3364

Max Act: 0.3215. Min Act: -0.0000

Data Index: 1036021 (C4 (Web Text))

Max Activating Token Index: 354

Text #6

Max Range: 0.3364. Min Range: -0.3364

Max Act: 0.2693. Min Act: -0.0000

Data Index: 674777 (C4 (Web Text))

Max Activating Token Index: 536

Text #7

Max Range: 0.3364. Min Range: -0.3364

Max Act: 0.2648. Min Act: -0.0000

Data Index: 602233 (C4 (Web Text))

Max Activating Token Index: 476

Text #8

Max Range: 0.3364. Min Range: -0.3364

Max Act: 0.2849. Min Act: -0.0000

Data Index: 1348611 (C4 (Web Text))

Max Activating Token Index: 781

Text #9

Max Range: 0.3364. Min Range: -0.3364

Max Act: 0.2538. Min Act: -0.0000

Data Index: 1062199 (C4 (Web Text))

Max Activating Token Index: 611

Text #10

Max Range: 0.3364. Min Range: -0.3364

Max Act: 0.2682. Min Act: -0.0000

Data Index: 660586 (C4 (Web Text))

Max Activating Token Index: 924

Text #11

Max Range: 0.3364. Min Range: -0.3364

Max Act: 0.2588. Min Act: -0.0000

Data Index: 155922 (C4 (Web Text))

Max Activating Token Index: 241

Text #12

Max Range: 0.3364. Min Range: -0.3364

Max Act: 0.2684. Min Act: -0.0000

Data Index: 703809 (C4 (Web Text))

Max Activating Token Index: 193

Text #13

Max Range: 0.3364. Min Range: -0.3364

Max Act: 0.2480. Min Act: -0.0000

Data Index: 951296 (C4 (Web Text))

Max Activating Token Index: 879

Text #14

Max Range: 0.3364. Min Range: -0.3364

Max Act: 0.2487. Min Act: -0.0000

Data Index: 468657 (C4 (Web Text))

Max Activating Token Index: 322

Text #15

Max Range: 0.3364. Min Range: -0.3364

Max Act: 0.2592. Min Act: -0.0000

Data Index: 1078128 (C4 (Web Text))

Max Activating Token Index: 441

Text #16

Max Range: 0.3364. Min Range: -0.3364

Max Act: 0.2541. Min Act: -0.0000

Data Index: 1567607 (Python Code)

Max Activating Token Index: 10

Text #17

Max Range: 0.3364. Min Range: -0.3364

Max Act: 0.2449. Min Act: -0.0000

Data Index: 334708 (C4 (Web Text))

Max Activating Token Index: 543

Text #18

Max Range: 0.3364. Min Range: -0.3364

Max Act: 0.2607. Min Act: -0.0000

Data Index: 1155055 (C4 (Web Text))

Max Activating Token Index: 624

Text #19

Max Range: 0.3364. Min Range: -0.3364

Max Act: 0.2522. Min Act: -0.0000

Data Index: 660511 (C4 (Web Text))

Max Activating Token Index: 69