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

Dataset: The Pile

Neuron 1460 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: 3.6321. Min Range: -3.6321

Max Act: 3.6321. Min Act: -0.0000

Data Index: 1322923 (The Pile)

Max Activating Token Index: 69

Text #1

Max Range: 3.6321. Min Range: -3.6321

Max Act: 3.2305. Min Act: -0.0000

Data Index: 170577 (The Pile)

Max Activating Token Index: 971

Text #2

Max Range: 3.6321. Min Range: -3.6321

Max Act: 2.8872. Min Act: -0.0000

Data Index: 735156 (The Pile)

Max Activating Token Index: 748

Text #3

Max Range: 3.6321. Min Range: -3.6321

Max Act: 2.6404. Min Act: -0.0000

Data Index: 825555 (The Pile)

Max Activating Token Index: 663

Text #4

Max Range: 3.6321. Min Range: -3.6321

Max Act: 2.5794. Min Act: -0.0000

Data Index: 1367938 (The Pile)

Max Activating Token Index: 98

Text #5

Max Range: 3.6321. Min Range: -3.6321

Max Act: 2.1712. Min Act: -0.0000

Data Index: 1758218 (The Pile)

Max Activating Token Index: 10

Text #6

Max Range: 3.6321. Min Range: -3.6321

Max Act: 2.2454. Min Act: -0.0000

Data Index: 711357 (The Pile)

Max Activating Token Index: 693

Text #7

Max Range: 3.6321. Min Range: -3.6321

Max Act: 2.3831. Min Act: -0.0000

Data Index: 1498907 (The Pile)

Max Activating Token Index: 250

Text #8

Max Range: 3.6321. Min Range: -3.6321

Max Act: 2.1496. Min Act: -0.0000

Data Index: 960805 (The Pile)

Max Activating Token Index: 457

Text #9

Max Range: 3.6321. Min Range: -3.6321

Max Act: 2.2302. Min Act: -0.0000

Data Index: 1895190 (The Pile)

Max Activating Token Index: 520

Text #10

Max Range: 3.6321. Min Range: -3.6321

Max Act: 2.1635. Min Act: -0.0000

Data Index: 1047995 (The Pile)

Max Activating Token Index: 790

Text #11

Max Range: 3.6321. Min Range: -3.6321

Max Act: 2.1415. Min Act: -0.0000

Data Index: 162417 (The Pile)

Max Activating Token Index: 787

Text #12

Max Range: 3.6321. Min Range: -3.6321

Max Act: 2.1277. Min Act: -0.0000

Data Index: 817663 (The Pile)

Max Activating Token Index: 755

Text #13

Max Range: 3.6321. Min Range: -3.6321

Max Act: 2.1333. Min Act: -0.0000

Data Index: 1841616 (The Pile)

Max Activating Token Index: 923

Text #14

Max Range: 3.6321. Min Range: -3.6321

Max Act: 2.2440. Min Act: -0.0000

Data Index: 1349389 (The Pile)

Max Activating Token Index: 367

Text #15

Max Range: 3.6321. Min Range: -3.6321

Max Act: 1.9740. Min Act: -0.0000

Data Index: 320476 (The Pile)

Max Activating Token Index: 450

Text #16

Max Range: 3.6321. Min Range: -3.6321

Max Act: 1.9702. Min Act: -0.0000

Data Index: 1297268 (The Pile)

Max Activating Token Index: 22

Text #17

Max Range: 3.6321. Min Range: -3.6321

Max Act: 2.0925. Min Act: -0.0000

Data Index: 1907415 (The Pile)

Max Activating Token Index: 680

Text #18

Max Range: 3.6321. Min Range: -3.6321

Max Act: 2.0611. Min Act: -0.0000

Data Index: 209079 (The Pile)

Max Activating Token Index: 344

Text #19

Max Range: 3.6321. Min Range: -3.6321

Max Act: 2.0552. Min Act: -0.0000

Data Index: 1603100 (The Pile)

Max Activating Token Index: 323