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

Dataset: The Pile

Neuron 2147 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: 1.1673. Min Range: -1.1673

Max Act: 1.1673. Min Act: -0.0000

Data Index: 1259597 (The Pile)

Max Activating Token Index: 238

Text #1

Max Range: 1.1673. Min Range: -1.1673

Max Act: 1.0390. Min Act: -0.0000

Data Index: 279582 (The Pile)

Max Activating Token Index: 87

Text #2

Max Range: 1.1673. Min Range: -1.1673

Max Act: 0.9837. Min Act: -0.0000

Data Index: 256433 (The Pile)

Max Activating Token Index: 751

Text #3

Max Range: 1.1673. Min Range: -1.1673

Max Act: 0.8782. Min Act: -0.0000

Data Index: 1286379 (The Pile)

Max Activating Token Index: 292

Text #4

Max Range: 1.1673. Min Range: -1.1673

Max Act: 0.9028. Min Act: -0.0000

Data Index: 1469210 (The Pile)

Max Activating Token Index: 277

Text #5

Max Range: 1.1673. Min Range: -1.1673

Max Act: 0.7871. Min Act: -0.0000

Data Index: 1323944 (The Pile)

Max Activating Token Index: 687

Text #6

Max Range: 1.1673. Min Range: -1.1673

Max Act: 0.7819. Min Act: -0.0000

Data Index: 1869023 (The Pile)

Max Activating Token Index: 36

Text #7

Max Range: 1.1673. Min Range: -1.1673

Max Act: 0.6933. Min Act: -0.0000

Data Index: 1171844 (The Pile)

Max Activating Token Index: 51

Text #8

Max Range: 1.1673. Min Range: -1.1673

Max Act: 0.7526. Min Act: -0.0000

Data Index: 971763 (The Pile)

Max Activating Token Index: 388

Text #9

Max Range: 1.1673. Min Range: -1.1673

Max Act: 0.7993. Min Act: -0.0000

Data Index: 708122 (The Pile)

Max Activating Token Index: 9

Text #10

Max Range: 1.1673. Min Range: -1.1673

Max Act: 0.6998. Min Act: -0.0000

Data Index: 1158718 (The Pile)

Max Activating Token Index: 531

Text #11

Max Range: 1.1673. Min Range: -1.1673

Max Act: 0.7597. Min Act: -0.0000

Data Index: 228953 (The Pile)

Max Activating Token Index: 200

Text #12

Max Range: 1.1673. Min Range: -1.1673

Max Act: 0.8592. Min Act: -0.0000

Data Index: 453897 (The Pile)

Max Activating Token Index: 833

Text #13

Max Range: 1.1673. Min Range: -1.1673

Max Act: 0.7782. Min Act: -0.0000

Data Index: 1271875 (The Pile)

Max Activating Token Index: 811

Text #14

Max Range: 1.1673. Min Range: -1.1673

Max Act: 0.7715. Min Act: -0.0000

Data Index: 675980 (The Pile)

Max Activating Token Index: 66

Text #15

Max Range: 1.1673. Min Range: -1.1673

Max Act: 0.7320. Min Act: -0.0000

Data Index: 1551366 (The Pile)

Max Activating Token Index: 936

Text #16

Max Range: 1.1673. Min Range: -1.1673

Max Act: 0.7212. Min Act: -0.0000

Data Index: 486825 (The Pile)

Max Activating Token Index: 474

Text #17

Max Range: 1.1673. Min Range: -1.1673

Max Act: 0.7085. Min Act: -0.0000

Data Index: 216741 (The Pile)

Max Activating Token Index: 475

Text #18

Max Range: 1.1673. Min Range: -1.1673

Max Act: 0.7328. Min Act: -0.0000

Data Index: 1826541 (The Pile)

Max Activating Token Index: 145

Text #19

Max Range: 1.1673. Min Range: -1.1673

Max Act: 0.6054. Min Act: -0.0000

Data Index: 840684 (The Pile)

Max Activating Token Index: 686