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

Dataset: The Pile

Neuron 1214 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4739. Min Range: -1.4739

Max Act: 1.4739. Min Act: -0.0000

Data Index: 202995 (The Pile)

Max Activating Token Index: 443

Text #1

Max Range: 1.4739. Min Range: -1.4739

Max Act: 1.3860. Min Act: -0.0000

Data Index: 380810 (The Pile)

Max Activating Token Index: 859

Text #2

Max Range: 1.4739. Min Range: -1.4739

Max Act: 1.3257. Min Act: -0.0000

Data Index: 294847 (The Pile)

Max Activating Token Index: 1007

Text #3

Max Range: 1.4739. Min Range: -1.4739

Max Act: 1.3447. Min Act: -0.0000

Data Index: 118977 (The Pile)

Max Activating Token Index: 632

Text #4

Max Range: 1.4739. Min Range: -1.4739

Max Act: 1.3183. Min Act: -0.0000

Data Index: 1657527 (The Pile)

Max Activating Token Index: 163

Text #5

Max Range: 1.4739. Min Range: -1.4739

Max Act: 1.3504. Min Act: -0.0000

Data Index: 913827 (The Pile)

Max Activating Token Index: 825

Text #6

Max Range: 1.4739. Min Range: -1.4739

Max Act: 1.2639. Min Act: -0.0001

Data Index: 780734 (The Pile)

Max Activating Token Index: 159

Text #7

Max Range: 1.4739. Min Range: -1.4739

Max Act: 1.2113. Min Act: -0.0000

Data Index: 1779800 (The Pile)

Max Activating Token Index: 560

Text #8

Max Range: 1.4739. Min Range: -1.4739

Max Act: 1.2602. Min Act: -0.0000

Data Index: 1312693 (The Pile)

Max Activating Token Index: 775

Text #9

Max Range: 1.4739. Min Range: -1.4739

Max Act: 1.1976. Min Act: -0.0000

Data Index: 1509899 (The Pile)

Max Activating Token Index: 614

Text #10

Max Range: 1.4739. Min Range: -1.4739

Max Act: 1.1480. Min Act: -0.0000

Data Index: 1730039 (The Pile)

Max Activating Token Index: 932

Text #11

Max Range: 1.4739. Min Range: -1.4739

Max Act: 1.2120. Min Act: -0.0000

Data Index: 1859421 (The Pile)

Max Activating Token Index: 171

Text #12

Max Range: 1.4739. Min Range: -1.4739

Max Act: 1.2337. Min Act: -0.0000

Data Index: 1362581 (The Pile)

Max Activating Token Index: 626

Text #13

Max Range: 1.4739. Min Range: -1.4739

Max Act: 1.1656. Min Act: -0.0000

Data Index: 1114886 (The Pile)

Max Activating Token Index: 21

Text #14

Max Range: 1.4739. Min Range: -1.4739

Max Act: 1.2202. Min Act: -0.0000

Data Index: 549789 (The Pile)

Max Activating Token Index: 34

Text #15

Max Range: 1.4739. Min Range: -1.4739

Max Act: 1.1554. Min Act: -0.0000

Data Index: 1133854 (The Pile)

Max Activating Token Index: 973

Text #16

Max Range: 1.4739. Min Range: -1.4739

Max Act: 1.2624. Min Act: -0.0000

Data Index: 842790 (The Pile)

Max Activating Token Index: 538

Text #17

Max Range: 1.4739. Min Range: -1.4739

Max Act: 1.1450. Min Act: -0.0000

Data Index: 1886027 (The Pile)

Max Activating Token Index: 291

Text #18

Max Range: 1.4739. Min Range: -1.4739

Max Act: 1.2137. Min Act: -0.0000

Data Index: 1318998 (The Pile)

Max Activating Token Index: 999

Text #19

Max Range: 1.4739. Min Range: -1.4739

Max Act: 1.1537. Min Act: -0.0000

Data Index: 990332 (The Pile)

Max Activating Token Index: 179