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

Dataset: The Pile

Neuron 3552 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: 1.2645. Min Range: -1.2645

Max Act: 1.2645. Min Act: -0.0000

Data Index: 1087986 (The Pile)

Max Activating Token Index: 823

Text #1

Max Range: 1.2645. Min Range: -1.2645

Max Act: 1.0262. Min Act: 0.0000

Data Index: 932996 (The Pile)

Max Activating Token Index: 895

Text #2

Max Range: 1.2645. Min Range: -1.2645

Max Act: 1.0034. Min Act: -0.0000

Data Index: 298049 (The Pile)

Max Activating Token Index: 418

Text #3

Max Range: 1.2645. Min Range: -1.2645

Max Act: 0.9654. Min Act: -0.0000

Data Index: 262546 (The Pile)

Max Activating Token Index: 472

Text #4

Max Range: 1.2645. Min Range: -1.2645

Max Act: 0.8449. Min Act: -0.0000

Data Index: 432112 (The Pile)

Max Activating Token Index: 165

Text #5

Max Range: 1.2645. Min Range: -1.2645

Max Act: 1.0134. Min Act: -0.0000

Data Index: 210135 (The Pile)

Max Activating Token Index: 246

Text #6

Max Range: 1.2645. Min Range: -1.2645

Max Act: 0.9736. Min Act: -0.0000

Data Index: 1437931 (The Pile)

Max Activating Token Index: 153

Text #7

Max Range: 1.2645. Min Range: -1.2645

Max Act: 0.9490. Min Act: -0.0000

Data Index: 659758 (The Pile)

Max Activating Token Index: 660

Text #8

Max Range: 1.2645. Min Range: -1.2645

Max Act: 0.8666. Min Act: -0.0000

Data Index: 308842 (The Pile)

Max Activating Token Index: 377

Text #9

Max Range: 1.2645. Min Range: -1.2645

Max Act: 0.8618. Min Act: -0.0000

Data Index: 818149 (The Pile)

Max Activating Token Index: 906

Text #10

Max Range: 1.2645. Min Range: -1.2645

Max Act: 0.8697. Min Act: -0.0000

Data Index: 929255 (The Pile)

Max Activating Token Index: 913

Text #11

Max Range: 1.2645. Min Range: -1.2645

Max Act: 0.9339. Min Act: -0.0000

Data Index: 1992312 (The Pile)

Max Activating Token Index: 986

Text #12

Max Range: 1.2645. Min Range: -1.2645

Max Act: 0.9485. Min Act: -0.0000

Data Index: 392415 (The Pile)

Max Activating Token Index: 124

Text #13

Max Range: 1.2645. Min Range: -1.2645

Max Act: 0.9157. Min Act: -0.0000

Data Index: 1855610 (The Pile)

Max Activating Token Index: 883

Text #14

Max Range: 1.2645. Min Range: -1.2645

Max Act: 0.8056. Min Act: 0.0000

Data Index: 923216 (The Pile)

Max Activating Token Index: 113

Text #15

Max Range: 1.2645. Min Range: -1.2645

Max Act: 0.8387. Min Act: -0.0000

Data Index: 1479472 (The Pile)

Max Activating Token Index: 778

Text #16

Max Range: 1.2645. Min Range: -1.2645

Max Act: 0.8320. Min Act: -0.0000

Data Index: 1226236 (The Pile)

Max Activating Token Index: 223

Text #17

Max Range: 1.2645. Min Range: -1.2645

Max Act: 0.8133. Min Act: -0.0000

Data Index: 1951771 (The Pile)

Max Activating Token Index: 432

Text #18

Max Range: 1.2645. Min Range: -1.2645

Max Act: 0.8391. Min Act: -0.0000

Data Index: 421184 (The Pile)

Max Activating Token Index: 237

Text #19

Max Range: 1.2645. Min Range: -1.2645

Max Act: 0.8083. Min Act: -0.0000

Data Index: 1736656 (The Pile)

Max Activating Token Index: 326