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

Dataset: The Pile

Neuron 949 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: 0.6262. Min Range: -0.6262

Max Act: 0.6262. Min Act: -0.0000

Data Index: 1270482 (The Pile)

Max Activating Token Index: 57

Text #1

Max Range: 0.6262. Min Range: -0.6262

Max Act: 0.5926. Min Act: -0.0000

Data Index: 1593907 (The Pile)

Max Activating Token Index: 310

Text #2

Max Range: 0.6262. Min Range: -0.6262

Max Act: 0.5422. Min Act: -0.0000

Data Index: 549955 (The Pile)

Max Activating Token Index: 215

Text #3

Max Range: 0.6262. Min Range: -0.6262

Max Act: 0.6107. Min Act: -0.0000

Data Index: 1536328 (The Pile)

Max Activating Token Index: 33

Text #4

Max Range: 0.6262. Min Range: -0.6262

Max Act: 0.5618. Min Act: -0.0000

Data Index: 409575 (The Pile)

Max Activating Token Index: 955

Text #5

Max Range: 0.6262. Min Range: -0.6262

Max Act: 0.5712. Min Act: -0.0000

Data Index: 244834 (The Pile)

Max Activating Token Index: 884

Text #6

Max Range: 0.6262. Min Range: -0.6262

Max Act: 0.5916. Min Act: -0.0000

Data Index: 871741 (The Pile)

Max Activating Token Index: 742

Text #7

Max Range: 0.6262. Min Range: -0.6262

Max Act: 0.5793. Min Act: -0.0000

Data Index: 725653 (The Pile)

Max Activating Token Index: 378

Text #8

Max Range: 0.6262. Min Range: -0.6262

Max Act: 0.5924. Min Act: -0.0000

Data Index: 24111 (The Pile)

Max Activating Token Index: 415

Text #9

Max Range: 0.6262. Min Range: -0.6262

Max Act: 0.5684. Min Act: -0.0000

Data Index: 846171 (The Pile)

Max Activating Token Index: 989

Text #10

Max Range: 0.6262. Min Range: -0.6262

Max Act: 0.5877. Min Act: -0.0000

Data Index: 1640891 (The Pile)

Max Activating Token Index: 673

Text #11

Max Range: 0.6262. Min Range: -0.6262

Max Act: 0.5874. Min Act: -0.0000

Data Index: 565118 (The Pile)

Max Activating Token Index: 103

Text #12

Max Range: 0.6262. Min Range: -0.6262

Max Act: 0.5797. Min Act: -0.0000

Data Index: 1864251 (The Pile)

Max Activating Token Index: 119

Text #13

Max Range: 0.6262. Min Range: -0.6262

Max Act: 0.5973. Min Act: -0.0000

Data Index: 1782406 (The Pile)

Max Activating Token Index: 893

Text #14

Max Range: 0.6262. Min Range: -0.6262

Max Act: 0.5358. Min Act: -0.0000

Data Index: 230717 (The Pile)

Max Activating Token Index: 540

Text #15

Max Range: 0.6262. Min Range: -0.6262

Max Act: 0.5279. Min Act: -0.0000

Data Index: 1178576 (The Pile)

Max Activating Token Index: 111

Text #16

Max Range: 0.6262. Min Range: -0.6262

Max Act: 0.4746. Min Act: -0.0000

Data Index: 655617 (The Pile)

Max Activating Token Index: 74

Text #17

Max Range: 0.6262. Min Range: -0.6262

Max Act: 0.5744. Min Act: -0.0000

Data Index: 623019 (The Pile)

Max Activating Token Index: 258

Text #18

Max Range: 0.6262. Min Range: -0.6262

Max Act: 0.5342. Min Act: -0.0000

Data Index: 895039 (The Pile)

Max Activating Token Index: 819

Text #19

Max Range: 0.6262. Min Range: -0.6262

Max Act: 0.5086. Min Act: -0.0000

Data Index: 308671 (The Pile)

Max Activating Token Index: 753