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

Dataset: The Pile

Neuron 279 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1046. Min Range: -1.1046

Max Act: 0.9593. Min Act: -0.0000

Data Index: 860327 (The Pile)

Max Activating Token Index: 815

Text #1

Max Range: 1.1046. Min Range: -1.1046

Max Act: 1.0725. Min Act: -0.0000

Data Index: 879722 (The Pile)

Max Activating Token Index: 893

Text #2

Max Range: 1.1046. Min Range: -1.1046

Max Act: 0.9076. Min Act: -0.0000

Data Index: 1060730 (The Pile)

Max Activating Token Index: 848

Text #3

Max Range: 1.1046. Min Range: -1.1046

Max Act: 0.8725. Min Act: -0.0000

Data Index: 1572309 (The Pile)

Max Activating Token Index: 235

Text #4

Max Range: 1.1046. Min Range: -1.1046

Max Act: 1.1046. Min Act: -0.0000

Data Index: 1331236 (The Pile)

Max Activating Token Index: 765

Text #5

Max Range: 1.1046. Min Range: -1.1046

Max Act: 0.9446. Min Act: -0.0000

Data Index: 985589 (The Pile)

Max Activating Token Index: 114

Text #6

Max Range: 1.1046. Min Range: -1.1046

Max Act: 0.9067. Min Act: -0.0000

Data Index: 1478993 (The Pile)

Max Activating Token Index: 95

Text #7

Max Range: 1.1046. Min Range: -1.1046

Max Act: 0.9099. Min Act: -0.0000

Data Index: 924663 (The Pile)

Max Activating Token Index: 299

Text #8

Max Range: 1.1046. Min Range: -1.1046

Max Act: 1.0093. Min Act: -0.0000

Data Index: 1419240 (The Pile)

Max Activating Token Index: 843

Text #9

Max Range: 1.1046. Min Range: -1.1046

Max Act: 0.8563. Min Act: -0.0000

Data Index: 1093010 (The Pile)

Max Activating Token Index: 735

Text #10

Max Range: 1.1046. Min Range: -1.1046

Max Act: 0.8902. Min Act: -0.0000

Data Index: 455652 (The Pile)

Max Activating Token Index: 925

Text #11

Max Range: 1.1046. Min Range: -1.1046

Max Act: 1.0661. Min Act: -0.0000

Data Index: 668728 (The Pile)

Max Activating Token Index: 885

Text #12

Max Range: 1.1046. Min Range: -1.1046

Max Act: 0.9554. Min Act: -0.0000

Data Index: 1286187 (The Pile)

Max Activating Token Index: 895

Text #13

Max Range: 1.1046. Min Range: -1.1046

Max Act: 0.8103. Min Act: -0.0000

Data Index: 421767 (The Pile)

Max Activating Token Index: 68

Text #14

Max Range: 1.1046. Min Range: -1.1046

Max Act: 0.8284. Min Act: -0.0000

Data Index: 1128634 (The Pile)

Max Activating Token Index: 164

Text #15

Max Range: 1.1046. Min Range: -1.1046

Max Act: 0.8020. Min Act: -0.0000

Data Index: 245289 (The Pile)

Max Activating Token Index: 619

Text #16

Max Range: 1.1046. Min Range: -1.1046

Max Act: 0.9269. Min Act: -0.0000

Data Index: 460751 (The Pile)

Max Activating Token Index: 266

Text #17

Max Range: 1.1046. Min Range: -1.1046

Max Act: 0.7390. Min Act: -0.0000

Data Index: 1160281 (The Pile)

Max Activating Token Index: 691

Text #18

Max Range: 1.1046. Min Range: -1.1046

Max Act: 0.7733. Min Act: -0.0000

Data Index: 111400 (The Pile)

Max Activating Token Index: 1007

Text #19

Max Range: 1.1046. Min Range: -1.1046

Max Act: 0.7508. Min Act: -0.0000

Data Index: 1526697 (The Pile)

Max Activating Token Index: 32