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

Dataset: The Pile

Neuron 2385 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2425. Min Range: -1.2425

Max Act: 1.2425. Min Act: -0.0000

Data Index: 638032 (The Pile)

Max Activating Token Index: 977

Text #1

Max Range: 1.2425. Min Range: -1.2425

Max Act: 1.2240. Min Act: -0.0000

Data Index: 1545240 (The Pile)

Max Activating Token Index: 295

Text #2

Max Range: 1.2425. Min Range: -1.2425

Max Act: 1.0812. Min Act: -0.0000

Data Index: 126567 (The Pile)

Max Activating Token Index: 404

Text #3

Max Range: 1.2425. Min Range: -1.2425

Max Act: 1.1733. Min Act: -0.0000

Data Index: 450100 (The Pile)

Max Activating Token Index: 593

Text #4

Max Range: 1.2425. Min Range: -1.2425

Max Act: 1.0410. Min Act: -0.0000

Data Index: 1510150 (The Pile)

Max Activating Token Index: 621

Text #5

Max Range: 1.2425. Min Range: -1.2425

Max Act: 0.9748. Min Act: -0.0000

Data Index: 1834342 (The Pile)

Max Activating Token Index: 77

Text #6

Max Range: 1.2425. Min Range: -1.2425

Max Act: 0.9704. Min Act: -0.0000

Data Index: 1286965 (The Pile)

Max Activating Token Index: 410

Text #7

Max Range: 1.2425. Min Range: -1.2425

Max Act: 0.9435. Min Act: -0.0000

Data Index: 1552095 (The Pile)

Max Activating Token Index: 405

Text #8

Max Range: 1.2425. Min Range: -1.2425

Max Act: 0.9955. Min Act: -0.0000

Data Index: 1864878 (The Pile)

Max Activating Token Index: 129

Text #9

Max Range: 1.2425. Min Range: -1.2425

Max Act: 1.0992. Min Act: -0.0000

Data Index: 878110 (The Pile)

Max Activating Token Index: 879

Text #10

Max Range: 1.2425. Min Range: -1.2425

Max Act: 0.9452. Min Act: -0.0000

Data Index: 1594486 (The Pile)

Max Activating Token Index: 954

Text #11

Max Range: 1.2425. Min Range: -1.2425

Max Act: 0.8655. Min Act: -0.0000

Data Index: 393612 (The Pile)

Max Activating Token Index: 695

Text #12

Max Range: 1.2425. Min Range: -1.2425

Max Act: 0.9737. Min Act: -0.0000

Data Index: 1664949 (The Pile)

Max Activating Token Index: 393

Text #13

Max Range: 1.2425. Min Range: -1.2425

Max Act: 0.7909. Min Act: -0.0000

Data Index: 1573880 (The Pile)

Max Activating Token Index: 42

Text #14

Max Range: 1.2425. Min Range: -1.2425

Max Act: 0.8452. Min Act: -0.0000

Data Index: 644145 (The Pile)

Max Activating Token Index: 460

Text #15

Max Range: 1.2425. Min Range: -1.2425

Max Act: 0.7822. Min Act: -0.0000

Data Index: 1784457 (The Pile)

Max Activating Token Index: 997

Text #16

Max Range: 1.2425. Min Range: -1.2425

Max Act: 0.7812. Min Act: -0.0000

Data Index: 1760976 (The Pile)

Max Activating Token Index: 391

Text #17

Max Range: 1.2425. Min Range: -1.2425

Max Act: 0.7627. Min Act: -0.0000

Data Index: 228682 (The Pile)

Max Activating Token Index: 994

Text #18

Max Range: 1.2425. Min Range: -1.2425

Max Act: 0.7668. Min Act: -0.0000

Data Index: 1430605 (The Pile)

Max Activating Token Index: 497

Text #19

Max Range: 1.2425. Min Range: -1.2425

Max Act: 0.8188. Min Act: -0.0000

Data Index: 959510 (The Pile)

Max Activating Token Index: 715