Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 1773 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.1049. Min Range: -1.1049

Max Act: 1.0844. Min Act: -0.0000

Data Index: 1969406 (The Pile)

Max Activating Token Index: 651

Text #1

Max Range: 1.1049. Min Range: -1.1049

Max Act: 1.1049. Min Act: -0.0000

Data Index: 52010 (The Pile)

Max Activating Token Index: 799

Text #2

Max Range: 1.1049. Min Range: -1.1049

Max Act: 0.9512. Min Act: -0.0000

Data Index: 545341 (The Pile)

Max Activating Token Index: 811

Text #3

Max Range: 1.1049. Min Range: -1.1049

Max Act: 1.0498. Min Act: -0.0000

Data Index: 1968191 (The Pile)

Max Activating Token Index: 329

Text #4

Max Range: 1.1049. Min Range: -1.1049

Max Act: 1.0124. Min Act: -0.0000

Data Index: 1238942 (The Pile)

Max Activating Token Index: 912

Text #5

Max Range: 1.1049. Min Range: -1.1049

Max Act: 0.9570. Min Act: -0.0000

Data Index: 1577711 (The Pile)

Max Activating Token Index: 563

Text #6

Max Range: 1.1049. Min Range: -1.1049

Max Act: 0.9092. Min Act: -0.0000

Data Index: 1710831 (The Pile)

Max Activating Token Index: 738

Text #7

Max Range: 1.1049. Min Range: -1.1049

Max Act: 0.8299. Min Act: -0.0000

Data Index: 1833351 (The Pile)

Max Activating Token Index: 749

Text #8

Max Range: 1.1049. Min Range: -1.1049

Max Act: 0.9568. Min Act: -0.0000

Data Index: 1323190 (The Pile)

Max Activating Token Index: 890

Text #9

Max Range: 1.1049. Min Range: -1.1049

Max Act: 0.8661. Min Act: -0.0000

Data Index: 1945536 (The Pile)

Max Activating Token Index: 610

Text #10

Max Range: 1.1049. Min Range: -1.1049

Max Act: 0.8402. Min Act: -0.0000

Data Index: 539879 (The Pile)

Max Activating Token Index: 981

Text #11

Max Range: 1.1049. Min Range: -1.1049

Max Act: 0.8262. Min Act: -0.0000

Data Index: 1978157 (The Pile)

Max Activating Token Index: 504

Text #12

Max Range: 1.1049. Min Range: -1.1049

Max Act: 0.8557. Min Act: -0.0000

Data Index: 288938 (The Pile)

Max Activating Token Index: 457

Text #13

Max Range: 1.1049. Min Range: -1.1049

Max Act: 0.9412. Min Act: -0.0000

Data Index: 1205066 (The Pile)

Max Activating Token Index: 795

Text #14

Max Range: 1.1049. Min Range: -1.1049

Max Act: 0.7619. Min Act: -0.0000

Data Index: 142644 (The Pile)

Max Activating Token Index: 687

Text #15

Max Range: 1.1049. Min Range: -1.1049

Max Act: 0.8503. Min Act: -0.0000

Data Index: 1289651 (The Pile)

Max Activating Token Index: 875

Text #16

Max Range: 1.1049. Min Range: -1.1049

Max Act: 0.8790. Min Act: -0.0000

Data Index: 783688 (The Pile)

Max Activating Token Index: 134

Text #17

Max Range: 1.1049. Min Range: -1.1049

Max Act: 0.8889. Min Act: -0.0000

Data Index: 367271 (The Pile)

Max Activating Token Index: 734

Text #18

Max Range: 1.1049. Min Range: -1.1049

Max Act: 0.7796. Min Act: -0.0000

Data Index: 947187 (The Pile)

Max Activating Token Index: 158

Text #19

Max Range: 1.1049. Min Range: -1.1049

Max Act: 0.6491. Min Act: -0.0000

Data Index: 1280449 (The Pile)

Max Activating Token Index: 482