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

Dataset: The Pile

Neuron 3042 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: 1.5226. Min Range: -1.5226

Max Act: 1.5226. Min Act: -0.0000

Data Index: 739799 (The Pile)

Max Activating Token Index: 500

Text #1

Max Range: 1.5226. Min Range: -1.5226

Max Act: 1.3602. Min Act: -0.0000

Data Index: 1339469 (The Pile)

Max Activating Token Index: 931

Text #2

Max Range: 1.5226. Min Range: -1.5226

Max Act: 1.2665. Min Act: -0.0000

Data Index: 391934 (The Pile)

Max Activating Token Index: 733

Text #3

Max Range: 1.5226. Min Range: -1.5226

Max Act: 1.0459. Min Act: 0.0000

Data Index: 1976088 (The Pile)

Max Activating Token Index: 76

Text #4

Max Range: 1.5226. Min Range: -1.5226

Max Act: 0.9979. Min Act: -0.0000

Data Index: 1415661 (The Pile)

Max Activating Token Index: 338

Text #5

Max Range: 1.5226. Min Range: -1.5226

Max Act: 0.9400. Min Act: 0.0000

Data Index: 1125116 (The Pile)

Max Activating Token Index: 239

Text #6

Max Range: 1.5226. Min Range: -1.5226

Max Act: 0.9481. Min Act: -0.0000

Data Index: 1158320 (The Pile)

Max Activating Token Index: 596

Text #7

Max Range: 1.5226. Min Range: -1.5226

Max Act: 0.7509. Min Act: -0.0000

Data Index: 162049 (The Pile)

Max Activating Token Index: 225

Text #8

Max Range: 1.5226. Min Range: -1.5226

Max Act: 0.8107. Min Act: -0.0000

Data Index: 938005 (The Pile)

Max Activating Token Index: 17

Text #9

Max Range: 1.5226. Min Range: -1.5226

Max Act: 0.8581. Min Act: -0.0000

Data Index: 1076680 (The Pile)

Max Activating Token Index: 897

Text #10

Max Range: 1.5226. Min Range: -1.5226

Max Act: 0.7303. Min Act: -0.0000

Data Index: 1589178 (The Pile)

Max Activating Token Index: 549

Text #11

Max Range: 1.5226. Min Range: -1.5226

Max Act: 0.6970. Min Act: -0.0000

Data Index: 1344951 (The Pile)

Max Activating Token Index: 823

Text #12

Max Range: 1.5226. Min Range: -1.5226

Max Act: 0.7084. Min Act: 0.0000

Data Index: 1103621 (The Pile)

Max Activating Token Index: 457

Text #13

Max Range: 1.5226. Min Range: -1.5226

Max Act: 0.7389. Min Act: -0.0000

Data Index: 1750826 (The Pile)

Max Activating Token Index: 817

Text #14

Max Range: 1.5226. Min Range: -1.5226

Max Act: 0.6457. Min Act: -0.0000

Data Index: 1842658 (The Pile)

Max Activating Token Index: 764

Text #15

Max Range: 1.5226. Min Range: -1.5226

Max Act: 0.7419. Min Act: 0.0000

Data Index: 1419510 (The Pile)

Max Activating Token Index: 173

Text #16

Max Range: 1.5226. Min Range: -1.5226

Max Act: 0.6899. Min Act: 0.0000

Data Index: 1361198 (The Pile)

Max Activating Token Index: 42

Text #17

Max Range: 1.5226. Min Range: -1.5226

Max Act: 0.7340. Min Act: -0.0000

Data Index: 857557 (The Pile)

Max Activating Token Index: 303

Text #18

Max Range: 1.5226. Min Range: -1.5226

Max Act: 0.6986. Min Act: -0.0000

Data Index: 1991602 (The Pile)

Max Activating Token Index: 418

Text #19

Max Range: 1.5226. Min Range: -1.5226

Max Act: 0.6501. Min Act: -0.0000

Data Index: 1780126 (The Pile)

Max Activating Token Index: 717