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

Dataset: The Pile

Neuron 977 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7584. Min Range: -3.7584

Max Act: 3.7584. Min Act: -0.0000

Data Index: 1106300 (The Pile)

Max Activating Token Index: 467

Text #1

Max Range: 3.7584. Min Range: -3.7584

Max Act: 3.7307. Min Act: -0.0000

Data Index: 1405932 (The Pile)

Max Activating Token Index: 698

Text #2

Max Range: 3.7584. Min Range: -3.7584

Max Act: 3.0717. Min Act: -0.0000

Data Index: 1208602 (The Pile)

Max Activating Token Index: 477

Text #3

Max Range: 3.7584. Min Range: -3.7584

Max Act: 3.0527. Min Act: -0.0000

Data Index: 161681 (The Pile)

Max Activating Token Index: 159

Text #4

Max Range: 3.7584. Min Range: -3.7584

Max Act: 3.0153. Min Act: -0.0000

Data Index: 533877 (The Pile)

Max Activating Token Index: 193

Text #5

Max Range: 3.7584. Min Range: -3.7584

Max Act: 2.7797. Min Act: -0.0000

Data Index: 562158 (The Pile)

Max Activating Token Index: 148

Text #6

Max Range: 3.7584. Min Range: -3.7584

Max Act: 2.9092. Min Act: -0.0000

Data Index: 690604 (The Pile)

Max Activating Token Index: 93

Text #7

Max Range: 3.7584. Min Range: -3.7584

Max Act: 2.8218. Min Act: -0.0000

Data Index: 1482469 (The Pile)

Max Activating Token Index: 427

Text #8

Max Range: 3.7584. Min Range: -3.7584

Max Act: 2.2290. Min Act: -0.0000

Data Index: 902854 (The Pile)

Max Activating Token Index: 290

Text #9

Max Range: 3.7584. Min Range: -3.7584

Max Act: 2.2111. Min Act: -0.0000

Data Index: 89524 (The Pile)

Max Activating Token Index: 617

Text #10

Max Range: 3.7584. Min Range: -3.7584

Max Act: 2.2497. Min Act: -0.0000

Data Index: 335910 (The Pile)

Max Activating Token Index: 718

Text #11

Max Range: 3.7584. Min Range: -3.7584

Max Act: 2.0051. Min Act: -0.0000

Data Index: 483576 (The Pile)

Max Activating Token Index: 792

Text #12

Max Range: 3.7584. Min Range: -3.7584

Max Act: 2.2991. Min Act: -0.0000

Data Index: 146999 (The Pile)

Max Activating Token Index: 746

Text #13

Max Range: 3.7584. Min Range: -3.7584

Max Act: 2.1543. Min Act: -0.0000

Data Index: 1155087 (The Pile)

Max Activating Token Index: 954

Text #14

Max Range: 3.7584. Min Range: -3.7584

Max Act: 1.8238. Min Act: -0.0000

Data Index: 1874923 (The Pile)

Max Activating Token Index: 848

Text #15

Max Range: 3.7584. Min Range: -3.7584

Max Act: 1.9786. Min Act: -0.0000

Data Index: 1983126 (The Pile)

Max Activating Token Index: 969

Text #16

Max Range: 3.7584. Min Range: -3.7584

Max Act: 1.8257. Min Act: -0.0000

Data Index: 1004728 (The Pile)

Max Activating Token Index: 503

Text #17

Max Range: 3.7584. Min Range: -3.7584

Max Act: 2.0139. Min Act: -0.0000

Data Index: 823935 (The Pile)

Max Activating Token Index: 133

Text #18

Max Range: 3.7584. Min Range: -3.7584

Max Act: 2.0547. Min Act: -0.0000

Data Index: 1080166 (The Pile)

Max Activating Token Index: 55

Text #19

Max Range: 3.7584. Min Range: -3.7584

Max Act: 1.7776. Min Act: -0.0000

Data Index: 1218451 (The Pile)

Max Activating Token Index: 640