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

Dataset: The Pile

Neuron 3746 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: 1.7959. Min Range: -1.7959

Max Act: 1.7959. Min Act: -0.0000

Data Index: 745547 (The Pile)

Max Activating Token Index: 656

Text #1

Max Range: 1.7959. Min Range: -1.7959

Max Act: 1.6571. Min Act: -0.0000

Data Index: 253543 (The Pile)

Max Activating Token Index: 437

Text #2

Max Range: 1.7959. Min Range: -1.7959

Max Act: 1.7306. Min Act: -0.0000

Data Index: 717610 (The Pile)

Max Activating Token Index: 802

Text #3

Max Range: 1.7959. Min Range: -1.7959

Max Act: 1.7678. Min Act: -0.0000

Data Index: 1641768 (The Pile)

Max Activating Token Index: 801

Text #4

Max Range: 1.7959. Min Range: -1.7959

Max Act: 1.6288. Min Act: -0.0000

Data Index: 1763661 (The Pile)

Max Activating Token Index: 917

Text #5

Max Range: 1.7959. Min Range: -1.7959

Max Act: 1.5930. Min Act: -0.0000

Data Index: 1441914 (The Pile)

Max Activating Token Index: 355

Text #6

Max Range: 1.7959. Min Range: -1.7959

Max Act: 1.6112. Min Act: -0.0000

Data Index: 905261 (The Pile)

Max Activating Token Index: 55

Text #7

Max Range: 1.7959. Min Range: -1.7959

Max Act: 1.4663. Min Act: -0.0000

Data Index: 553693 (The Pile)

Max Activating Token Index: 579

Text #8

Max Range: 1.7959. Min Range: -1.7959

Max Act: 1.4477. Min Act: -0.0000

Data Index: 990694 (The Pile)

Max Activating Token Index: 671

Text #9

Max Range: 1.7959. Min Range: -1.7959

Max Act: 1.4189. Min Act: -0.0000

Data Index: 1089124 (The Pile)

Max Activating Token Index: 307

Text #10

Max Range: 1.7959. Min Range: -1.7959

Max Act: 1.3764. Min Act: -0.0000

Data Index: 972159 (The Pile)

Max Activating Token Index: 195

Text #11

Max Range: 1.7959. Min Range: -1.7959

Max Act: 1.3484. Min Act: -0.0000

Data Index: 424638 (The Pile)

Max Activating Token Index: 915

Text #12

Max Range: 1.7959. Min Range: -1.7959

Max Act: 1.4105. Min Act: -0.0000

Data Index: 57608 (The Pile)

Max Activating Token Index: 960

Text #13

Max Range: 1.7959. Min Range: -1.7959

Max Act: 1.4090. Min Act: -0.0000

Data Index: 636339 (The Pile)

Max Activating Token Index: 426

Text #14

Max Range: 1.7959. Min Range: -1.7959

Max Act: 1.3083. Min Act: -0.0000

Data Index: 1684470 (The Pile)

Max Activating Token Index: 740

Text #15

Max Range: 1.7959. Min Range: -1.7959

Max Act: 1.3956. Min Act: -0.0000

Data Index: 508921 (The Pile)

Max Activating Token Index: 1008

Text #16

Max Range: 1.7959. Min Range: -1.7959

Max Act: 1.2991. Min Act: -0.0000

Data Index: 1836660 (The Pile)

Max Activating Token Index: 997

Text #17

Max Range: 1.7959. Min Range: -1.7959

Max Act: 1.2007. Min Act: -0.0000

Data Index: 1889020 (The Pile)

Max Activating Token Index: 619

Text #18

Max Range: 1.7959. Min Range: -1.7959

Max Act: 1.2586. Min Act: -0.0000

Data Index: 323533 (The Pile)

Max Activating Token Index: 347

Text #19

Max Range: 1.7959. Min Range: -1.7959

Max Act: 1.2536. Min Act: -0.0000

Data Index: 1789234 (The Pile)

Max Activating Token Index: 522