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

Dataset: The Pile

Neuron 2839 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6994. Min Range: -1.6994

Max Act: 1.6994. Min Act: -0.0000

Data Index: 162571 (The Pile)

Max Activating Token Index: 957

Text #1

Max Range: 1.6994. Min Range: -1.6994

Max Act: 1.6199. Min Act: -0.0000

Data Index: 1488679 (The Pile)

Max Activating Token Index: 315

Text #2

Max Range: 1.6994. Min Range: -1.6994

Max Act: 1.4523. Min Act: -0.0000

Data Index: 423489 (The Pile)

Max Activating Token Index: 122

Text #3

Max Range: 1.6994. Min Range: -1.6994

Max Act: 1.4296. Min Act: -0.0000

Data Index: 942557 (The Pile)

Max Activating Token Index: 96

Text #4

Max Range: 1.6994. Min Range: -1.6994

Max Act: 1.1943. Min Act: -0.0000

Data Index: 338366 (The Pile)

Max Activating Token Index: 693

Text #5

Max Range: 1.6994. Min Range: -1.6994

Max Act: 1.3152. Min Act: -0.0000

Data Index: 1437727 (The Pile)

Max Activating Token Index: 466

Text #6

Max Range: 1.6994. Min Range: -1.6994

Max Act: 1.2226. Min Act: -0.0000

Data Index: 887219 (The Pile)

Max Activating Token Index: 693

Text #7

Max Range: 1.6994. Min Range: -1.6994

Max Act: 1.2111. Min Act: -0.0000

Data Index: 1657885 (The Pile)

Max Activating Token Index: 479

Text #8

Max Range: 1.6994. Min Range: -1.6994

Max Act: 1.2199. Min Act: -0.0000

Data Index: 1164760 (The Pile)

Max Activating Token Index: 920

Text #9

Max Range: 1.6994. Min Range: -1.6994

Max Act: 1.3181. Min Act: -0.0000

Data Index: 1247424 (The Pile)

Max Activating Token Index: 817

Text #10

Max Range: 1.6994. Min Range: -1.6994

Max Act: 1.2272. Min Act: -0.0000

Data Index: 1191959 (The Pile)

Max Activating Token Index: 273

Text #11

Max Range: 1.6994. Min Range: -1.6994

Max Act: 1.0784. Min Act: -0.0000

Data Index: 1905044 (The Pile)

Max Activating Token Index: 369

Text #12

Max Range: 1.6994. Min Range: -1.6994

Max Act: 1.2027. Min Act: -0.0000

Data Index: 1746393 (The Pile)

Max Activating Token Index: 364

Text #13

Max Range: 1.6994. Min Range: -1.6994

Max Act: 1.3427. Min Act: -0.0000

Data Index: 1351525 (The Pile)

Max Activating Token Index: 930

Text #14

Max Range: 1.6994. Min Range: -1.6994

Max Act: 1.1588. Min Act: -0.0000

Data Index: 362256 (The Pile)

Max Activating Token Index: 356

Text #15

Max Range: 1.6994. Min Range: -1.6994

Max Act: 1.2613. Min Act: -0.0000

Data Index: 1648214 (The Pile)

Max Activating Token Index: 821

Text #16

Max Range: 1.6994. Min Range: -1.6994

Max Act: 1.1815. Min Act: -0.0000

Data Index: 329569 (The Pile)

Max Activating Token Index: 76

Text #17

Max Range: 1.6994. Min Range: -1.6994

Max Act: 1.0960. Min Act: -0.0000

Data Index: 346012 (The Pile)

Max Activating Token Index: 933

Text #18

Max Range: 1.6994. Min Range: -1.6994

Max Act: 1.2119. Min Act: -0.0000

Data Index: 683157 (The Pile)

Max Activating Token Index: 997

Text #19

Max Range: 1.6994. Min Range: -1.6994

Max Act: 1.1345. Min Act: -0.0000

Data Index: 167758 (The Pile)

Max Activating Token Index: 654