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

Dataset: The Pile

Neuron 2297 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: 0.9917. Min Range: -0.9917

Max Act: 0.9917. Min Act: 0.0000

Data Index: 472523 (The Pile)

Max Activating Token Index: 263

Text #1

Max Range: 0.9917. Min Range: -0.9917

Max Act: 0.8936. Min Act: 0.0000

Data Index: 409017 (The Pile)

Max Activating Token Index: 34

Text #2

Max Range: 0.9917. Min Range: -0.9917

Max Act: 0.9715. Min Act: -0.0000

Data Index: 1552904 (The Pile)

Max Activating Token Index: 888

Text #3

Max Range: 0.9917. Min Range: -0.9917

Max Act: 0.8118. Min Act: -0.0000

Data Index: 167191 (The Pile)

Max Activating Token Index: 337

Text #4

Max Range: 0.9917. Min Range: -0.9917

Max Act: 0.7832. Min Act: -0.0000

Data Index: 1276261 (The Pile)

Max Activating Token Index: 360

Text #5

Max Range: 0.9917. Min Range: -0.9917

Max Act: 0.7978. Min Act: -0.0000

Data Index: 980419 (The Pile)

Max Activating Token Index: 870

Text #6

Max Range: 0.9917. Min Range: -0.9917

Max Act: 0.8400. Min Act: -0.0000

Data Index: 1161189 (The Pile)

Max Activating Token Index: 777

Text #7

Max Range: 0.9917. Min Range: -0.9917

Max Act: 0.7578. Min Act: -0.0000

Data Index: 1640818 (The Pile)

Max Activating Token Index: 908

Text #8

Max Range: 0.9917. Min Range: -0.9917

Max Act: 0.7411. Min Act: -0.0000

Data Index: 238850 (The Pile)

Max Activating Token Index: 262

Text #9

Max Range: 0.9917. Min Range: -0.9917

Max Act: 0.6848. Min Act: -0.0000

Data Index: 1638769 (The Pile)

Max Activating Token Index: 491

Text #10

Max Range: 0.9917. Min Range: -0.9917

Max Act: 0.6724. Min Act: -0.0000

Data Index: 1098101 (The Pile)

Max Activating Token Index: 666

Text #11

Max Range: 0.9917. Min Range: -0.9917

Max Act: 0.7106. Min Act: -0.0000

Data Index: 1115023 (The Pile)

Max Activating Token Index: 979

Text #12

Max Range: 0.9917. Min Range: -0.9917

Max Act: 0.6814. Min Act: -0.0000

Data Index: 1485283 (The Pile)

Max Activating Token Index: 85

Text #13

Max Range: 0.9917. Min Range: -0.9917

Max Act: 0.7087. Min Act: 0.0000

Data Index: 1402252 (The Pile)

Max Activating Token Index: 634

Text #14

Max Range: 0.9917. Min Range: -0.9917

Max Act: 0.7333. Min Act: -0.0000

Data Index: 231597 (The Pile)

Max Activating Token Index: 759

Text #15

Max Range: 0.9917. Min Range: -0.9917

Max Act: 0.6561. Min Act: -0.0000

Data Index: 934650 (The Pile)

Max Activating Token Index: 839

Text #16

Max Range: 0.9917. Min Range: -0.9917

Max Act: 0.6538. Min Act: -0.0000

Data Index: 1950255 (The Pile)

Max Activating Token Index: 64

Text #17

Max Range: 0.9917. Min Range: -0.9917

Max Act: 0.6334. Min Act: 0.0001

Data Index: 295928 (The Pile)

Max Activating Token Index: 716

Text #18

Max Range: 0.9917. Min Range: -0.9917

Max Act: 0.6215. Min Act: -0.0000

Data Index: 1530676 (The Pile)

Max Activating Token Index: 897

Text #19

Max Range: 0.9917. Min Range: -0.9917

Max Act: 0.6057. Min Act: -0.0000

Data Index: 23205 (The Pile)

Max Activating Token Index: 68