Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 3996 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.9978. Min Range: -0.9978

Max Act: 0.9724. Min Act: -0.0000

Data Index: 1438019 (The Pile)

Max Activating Token Index: 840

Text #1

Max Range: 0.9978. Min Range: -0.9978

Max Act: 0.9021. Min Act: -0.0000

Data Index: 1432204 (The Pile)

Max Activating Token Index: 554

Text #2

Max Range: 0.9978. Min Range: -0.9978

Max Act: 0.9978. Min Act: -0.0000

Data Index: 1863577 (The Pile)

Max Activating Token Index: 641

Text #3

Max Range: 0.9978. Min Range: -0.9978

Max Act: 0.8877. Min Act: -0.0000

Data Index: 191447 (The Pile)

Max Activating Token Index: 389

Text #4

Max Range: 0.9978. Min Range: -0.9978

Max Act: 0.7576. Min Act: -0.0000

Data Index: 58179 (The Pile)

Max Activating Token Index: 199

Text #5

Max Range: 0.9978. Min Range: -0.9978

Max Act: 0.7983. Min Act: -0.0000

Data Index: 1453492 (The Pile)

Max Activating Token Index: 405

Text #6

Max Range: 0.9978. Min Range: -0.9978

Max Act: 0.8413. Min Act: -0.0000

Data Index: 803565 (The Pile)

Max Activating Token Index: 391

Text #7

Max Range: 0.9978. Min Range: -0.9978

Max Act: 0.7636. Min Act: -0.0000

Data Index: 1223957 (The Pile)

Max Activating Token Index: 699

Text #8

Max Range: 0.9978. Min Range: -0.9978

Max Act: 0.7643. Min Act: -0.0000

Data Index: 1620764 (The Pile)

Max Activating Token Index: 599

Text #9

Max Range: 0.9978. Min Range: -0.9978

Max Act: 0.8717. Min Act: -0.0000

Data Index: 770927 (The Pile)

Max Activating Token Index: 647

Text #10

Max Range: 0.9978. Min Range: -0.9978

Max Act: 0.7494. Min Act: -0.0000

Data Index: 665990 (The Pile)

Max Activating Token Index: 85

Text #11

Max Range: 0.9978. Min Range: -0.9978

Max Act: 0.7432. Min Act: -0.0000

Data Index: 603094 (The Pile)

Max Activating Token Index: 280

Text #12

Max Range: 0.9978. Min Range: -0.9978

Max Act: 0.6527. Min Act: -0.0000

Data Index: 202412 (The Pile)

Max Activating Token Index: 989

Text #13

Max Range: 0.9978. Min Range: -0.9978

Max Act: 0.6938. Min Act: -0.0000

Data Index: 485963 (The Pile)

Max Activating Token Index: 344

Text #14

Max Range: 0.9978. Min Range: -0.9978

Max Act: 0.6845. Min Act: -0.0000

Data Index: 1699046 (The Pile)

Max Activating Token Index: 123

Text #15

Max Range: 0.9978. Min Range: -0.9978

Max Act: 0.6764. Min Act: -0.0000

Data Index: 1610784 (The Pile)

Max Activating Token Index: 374

Text #16

Max Range: 0.9978. Min Range: -0.9978

Max Act: 0.6339. Min Act: -0.0000

Data Index: 1459526 (The Pile)

Max Activating Token Index: 95

Text #17

Max Range: 0.9978. Min Range: -0.9978

Max Act: 0.6749. Min Act: -0.0000

Data Index: 1371429 (The Pile)

Max Activating Token Index: 819

Text #18

Max Range: 0.9978. Min Range: -0.9978

Max Act: 0.7315. Min Act: -0.0000

Data Index: 931651 (The Pile)

Max Activating Token Index: 445

Text #19

Max Range: 0.9978. Min Range: -0.9978

Max Act: 0.6264. Min Act: -0.0000

Data Index: 83545 (The Pile)

Max Activating Token Index: 113