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

Dataset: The Pile

Neuron 996 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3454. Min Range: -0.3454

Max Act: 0.3240. Min Act: -0.0000

Data Index: 23785 (The Pile)

Max Activating Token Index: 134

Text #1

Max Range: 0.3454. Min Range: -0.3454

Max Act: 0.3454. Min Act: -0.0000

Data Index: 746276 (The Pile)

Max Activating Token Index: 703

Text #2

Max Range: 0.3454. Min Range: -0.3454

Max Act: 0.3247. Min Act: -0.0000

Data Index: 1576468 (The Pile)

Max Activating Token Index: 401

Text #3

Max Range: 0.3454. Min Range: -0.3454

Max Act: 0.2986. Min Act: -0.0000

Data Index: 1276499 (The Pile)

Max Activating Token Index: 286

Text #4

Max Range: 0.3454. Min Range: -0.3454

Max Act: 0.3194. Min Act: -0.0000

Data Index: 524471 (The Pile)

Max Activating Token Index: 893

Text #5

Max Range: 0.3454. Min Range: -0.3454

Max Act: 0.3023. Min Act: -0.0000

Data Index: 690592 (The Pile)

Max Activating Token Index: 124

Text #6

Max Range: 0.3454. Min Range: -0.3454

Max Act: 0.2721. Min Act: -0.0000

Data Index: 816528 (The Pile)

Max Activating Token Index: 58

Text #7

Max Range: 0.3454. Min Range: -0.3454

Max Act: 0.2978. Min Act: -0.0000

Data Index: 1884480 (The Pile)

Max Activating Token Index: 129

Text #8

Max Range: 0.3454. Min Range: -0.3454

Max Act: 0.2875. Min Act: -0.0000

Data Index: 1430483 (The Pile)

Max Activating Token Index: 493

Text #9

Max Range: 0.3454. Min Range: -0.3454

Max Act: 0.2973. Min Act: -0.0000

Data Index: 1409560 (The Pile)

Max Activating Token Index: 458

Text #10

Max Range: 0.3454. Min Range: -0.3454

Max Act: 0.2912. Min Act: -0.0000

Data Index: 1562971 (The Pile)

Max Activating Token Index: 205

Text #11

Max Range: 0.3454. Min Range: -0.3454

Max Act: 0.2896. Min Act: -0.0000

Data Index: 1016824 (The Pile)

Max Activating Token Index: 862

Text #12

Max Range: 0.3454. Min Range: -0.3454

Max Act: 0.2597. Min Act: -0.0000

Data Index: 196965 (The Pile)

Max Activating Token Index: 102

Text #13

Max Range: 0.3454. Min Range: -0.3454

Max Act: 0.2590. Min Act: -0.0000

Data Index: 1334070 (The Pile)

Max Activating Token Index: 137

Text #14

Max Range: 0.3454. Min Range: -0.3454

Max Act: 0.2668. Min Act: -0.0000

Data Index: 931184 (The Pile)

Max Activating Token Index: 726

Text #15

Max Range: 0.3454. Min Range: -0.3454

Max Act: 0.2894. Min Act: -0.0000

Data Index: 727711 (The Pile)

Max Activating Token Index: 838

Text #16

Max Range: 0.3454. Min Range: -0.3454

Max Act: 0.2683. Min Act: -0.0000

Data Index: 1393781 (The Pile)

Max Activating Token Index: 384

Text #17

Max Range: 0.3454. Min Range: -0.3454

Max Act: 0.2618. Min Act: -0.0000

Data Index: 673476 (The Pile)

Max Activating Token Index: 864

Text #18

Max Range: 0.3454. Min Range: -0.3454

Max Act: 0.2525. Min Act: -0.0000

Data Index: 291668 (The Pile)

Max Activating Token Index: 832

Text #19

Max Range: 0.3454. Min Range: -0.3454

Max Act: 0.2578. Min Act: -0.0000

Data Index: 288915 (The Pile)

Max Activating Token Index: 508