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

Dataset: The Pile

Neuron 3 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9405. Min Range: -0.9405

Max Act: 0.9405. Min Act: -0.0000

Data Index: 1423905 (The Pile)

Max Activating Token Index: 756

Text #1

Max Range: 0.9405. Min Range: -0.9405

Max Act: 0.6634. Min Act: -0.0000

Data Index: 642057 (The Pile)

Max Activating Token Index: 316

Text #2

Max Range: 0.9405. Min Range: -0.9405

Max Act: 0.5974. Min Act: -0.0000

Data Index: 939631 (The Pile)

Max Activating Token Index: 279

Text #3

Max Range: 0.9405. Min Range: -0.9405

Max Act: 0.5567. Min Act: -0.0000

Data Index: 1038293 (The Pile)

Max Activating Token Index: 1014

Text #4

Max Range: 0.9405. Min Range: -0.9405

Max Act: 0.5694. Min Act: -0.0000

Data Index: 1762555 (The Pile)

Max Activating Token Index: 81

Text #5

Max Range: 0.9405. Min Range: -0.9405

Max Act: 0.5168. Min Act: -0.0000

Data Index: 570777 (The Pile)

Max Activating Token Index: 557

Text #6

Max Range: 0.9405. Min Range: -0.9405

Max Act: 0.5206. Min Act: -0.0000

Data Index: 1033845 (The Pile)

Max Activating Token Index: 222

Text #7

Max Range: 0.9405. Min Range: -0.9405

Max Act: 0.4830. Min Act: -0.0000

Data Index: 1202075 (The Pile)

Max Activating Token Index: 746

Text #8

Max Range: 0.9405. Min Range: -0.9405

Max Act: 0.5318. Min Act: -0.0000

Data Index: 16628 (The Pile)

Max Activating Token Index: 82

Text #9

Max Range: 0.9405. Min Range: -0.9405

Max Act: 0.5152. Min Act: -0.0000

Data Index: 550059 (The Pile)

Max Activating Token Index: 954

Text #10

Max Range: 0.9405. Min Range: -0.9405

Max Act: 0.5034. Min Act: -0.0000

Data Index: 1770690 (The Pile)

Max Activating Token Index: 660

Text #11

Max Range: 0.9405. Min Range: -0.9405

Max Act: 0.4457. Min Act: -0.0000

Data Index: 1942769 (The Pile)

Max Activating Token Index: 750

Text #12

Max Range: 0.9405. Min Range: -0.9405

Max Act: 0.4495. Min Act: -0.0000

Data Index: 1717767 (The Pile)

Max Activating Token Index: 700

Text #13

Max Range: 0.9405. Min Range: -0.9405

Max Act: 0.4723. Min Act: -0.0000

Data Index: 1965533 (The Pile)

Max Activating Token Index: 707

Text #14

Max Range: 0.9405. Min Range: -0.9405

Max Act: 0.4618. Min Act: -0.0000

Data Index: 139048 (The Pile)

Max Activating Token Index: 695

Text #15

Max Range: 0.9405. Min Range: -0.9405

Max Act: 0.4502. Min Act: -0.0000

Data Index: 781385 (The Pile)

Max Activating Token Index: 797

Text #16

Max Range: 0.9405. Min Range: -0.9405

Max Act: 0.4660. Min Act: -0.0000

Data Index: 1427906 (The Pile)

Max Activating Token Index: 53

Text #17

Max Range: 0.9405. Min Range: -0.9405

Max Act: 0.4438. Min Act: -0.0000

Data Index: 410411 (The Pile)

Max Activating Token Index: 299

Text #18

Max Range: 0.9405. Min Range: -0.9405

Max Act: 0.4753. Min Act: -0.0000

Data Index: 1233684 (The Pile)

Max Activating Token Index: 538

Text #19

Max Range: 0.9405. Min Range: -0.9405

Max Act: 0.4831. Min Act: 0.0000

Data Index: 1756047 (The Pile)

Max Activating Token Index: 954