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

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

Neuron 3871 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0584. Min Act: -0.0001

Data Index: 606477 (C4 (Web Text))

Max Activating Token Index: 72

Text #1

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0496. Min Act: -0.0001

Data Index: 1194483 (C4 (Web Text))

Max Activating Token Index: 600

Text #2

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0456. Min Act: -0.0001

Data Index: 302135 (C4 (Web Text))

Max Activating Token Index: 5

Text #3

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0452. Min Act: -0.0002

Data Index: 1011151 (C4 (Web Text))

Max Activating Token Index: 962

Text #4

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0467. Min Act: -0.0001

Data Index: 1317036 (C4 (Web Text))

Max Activating Token Index: 13

Text #5

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0481. Min Act: -0.0002

Data Index: 1094599 (C4 (Web Text))

Max Activating Token Index: 781

Text #6

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0461. Min Act: -0.0002

Data Index: 995461 (C4 (Web Text))

Max Activating Token Index: 793

Text #7

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0481. Min Act: -0.0001

Data Index: 62729 (C4 (Web Text))

Max Activating Token Index: 619

Text #8

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0454. Min Act: -0.0001

Data Index: 15054 (C4 (Web Text))

Max Activating Token Index: 41

Text #9

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0421. Min Act: -0.0001

Data Index: 633686 (C4 (Web Text))

Max Activating Token Index: 988

Text #10

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0416. Min Act: -0.0002

Data Index: 684901 (C4 (Web Text))

Max Activating Token Index: 987

Text #11

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0437. Min Act: -0.0001

Data Index: 942458 (C4 (Web Text))

Max Activating Token Index: 934

Text #12

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0423. Min Act: -0.0002

Data Index: 235723 (C4 (Web Text))

Max Activating Token Index: 357

Text #13

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0423. Min Act: -0.0001

Data Index: 615558 (C4 (Web Text))

Max Activating Token Index: 9

Text #14

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0420. Min Act: -0.0001

Data Index: 236653 (C4 (Web Text))

Max Activating Token Index: 9

Text #15

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0407. Min Act: -0.0001

Data Index: 905904 (C4 (Web Text))

Max Activating Token Index: 60

Text #16

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0404. Min Act: -0.0002

Data Index: 969659 (C4 (Web Text))

Max Activating Token Index: 537

Text #17

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0414. Min Act: -0.0002

Data Index: 506454 (C4 (Web Text))

Max Activating Token Index: 893

Text #18

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0416. Min Act: -0.0002

Data Index: 1084359 (C4 (Web Text))

Max Activating Token Index: 460

Text #19

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0397. Min Act: -0.0002

Data Index: 863867 (C4 (Web Text))

Max Activating Token Index: 325