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

Dataset: The Pile

Neuron 3933 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8426. Min Range: -0.8426

Max Act: 0.8426. Min Act: -0.0000

Data Index: 207537 (The Pile)

Max Activating Token Index: 860

Text #1

Max Range: 0.8426. Min Range: -0.8426

Max Act: 0.7964. Min Act: -0.0000

Data Index: 1196751 (The Pile)

Max Activating Token Index: 262

Text #2

Max Range: 0.8426. Min Range: -0.8426

Max Act: 0.7623. Min Act: -0.0000

Data Index: 1078958 (The Pile)

Max Activating Token Index: 356

Text #3

Max Range: 0.8426. Min Range: -0.8426

Max Act: 0.8023. Min Act: -0.0000

Data Index: 1322556 (The Pile)

Max Activating Token Index: 31

Text #4

Max Range: 0.8426. Min Range: -0.8426

Max Act: 0.7728. Min Act: -0.0000

Data Index: 1038463 (The Pile)

Max Activating Token Index: 956

Text #5

Max Range: 0.8426. Min Range: -0.8426

Max Act: 0.8173. Min Act: -0.0000

Data Index: 914132 (The Pile)

Max Activating Token Index: 400

Text #6

Max Range: 0.8426. Min Range: -0.8426

Max Act: 0.7689. Min Act: -0.0000

Data Index: 545747 (The Pile)

Max Activating Token Index: 186

Text #7

Max Range: 0.8426. Min Range: -0.8426

Max Act: 0.7901. Min Act: -0.0000

Data Index: 647860 (The Pile)

Max Activating Token Index: 820

Text #8

Max Range: 0.8426. Min Range: -0.8426

Max Act: 0.7201. Min Act: -0.0000

Data Index: 1128871 (The Pile)

Max Activating Token Index: 738

Text #9

Max Range: 0.8426. Min Range: -0.8426

Max Act: 0.7906. Min Act: -0.0000

Data Index: 508044 (The Pile)

Max Activating Token Index: 248

Text #10

Max Range: 0.8426. Min Range: -0.8426

Max Act: 0.7633. Min Act: -0.0000

Data Index: 202136 (The Pile)

Max Activating Token Index: 488

Text #11

Max Range: 0.8426. Min Range: -0.8426

Max Act: 0.7619. Min Act: -0.0000

Data Index: 405970 (The Pile)

Max Activating Token Index: 309

Text #12

Max Range: 0.8426. Min Range: -0.8426

Max Act: 0.7568. Min Act: -0.0000

Data Index: 1649070 (The Pile)

Max Activating Token Index: 42

Text #13

Max Range: 0.8426. Min Range: -0.8426

Max Act: 0.7846. Min Act: -0.0000

Data Index: 86456 (The Pile)

Max Activating Token Index: 545

Text #14

Max Range: 0.8426. Min Range: -0.8426

Max Act: 0.7156. Min Act: -0.0000

Data Index: 1206293 (The Pile)

Max Activating Token Index: 653

Text #15

Max Range: 0.8426. Min Range: -0.8426

Max Act: 0.7634. Min Act: -0.0000

Data Index: 282450 (The Pile)

Max Activating Token Index: 682

Text #16

Max Range: 0.8426. Min Range: -0.8426

Max Act: 0.7797. Min Act: -0.0000

Data Index: 1261230 (The Pile)

Max Activating Token Index: 911

Text #17

Max Range: 0.8426. Min Range: -0.8426

Max Act: 0.7540. Min Act: -0.0000

Data Index: 538418 (The Pile)

Max Activating Token Index: 195

Text #18

Max Range: 0.8426. Min Range: -0.8426

Max Act: 0.7997. Min Act: -0.0000

Data Index: 157297 (The Pile)

Max Activating Token Index: 939

Text #19

Max Range: 0.8426. Min Range: -0.8426

Max Act: 0.7999. Min Act: -0.0000

Data Index: 277348 (The Pile)

Max Activating Token Index: 456