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

Dataset: The Pile

Neuron 195 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: 3.8906. Min Range: -3.8906

Max Act: 3.8906. Min Act: -0.0000

Data Index: 775776 (The Pile)

Max Activating Token Index: 348

Text #1

Max Range: 3.8906. Min Range: -3.8906

Max Act: 3.6252. Min Act: -0.0000

Data Index: 479401 (The Pile)

Max Activating Token Index: 505

Text #2

Max Range: 3.8906. Min Range: -3.8906

Max Act: 3.6179. Min Act: -0.0000

Data Index: 728383 (The Pile)

Max Activating Token Index: 289

Text #3

Max Range: 3.8906. Min Range: -3.8906

Max Act: 3.5570. Min Act: -0.0000

Data Index: 700093 (The Pile)

Max Activating Token Index: 340

Text #4

Max Range: 3.8906. Min Range: -3.8906

Max Act: 3.3531. Min Act: -0.0000

Data Index: 254461 (The Pile)

Max Activating Token Index: 341

Text #5

Max Range: 3.8906. Min Range: -3.8906

Max Act: 3.1592. Min Act: -0.0000

Data Index: 1566830 (The Pile)

Max Activating Token Index: 622

Text #6

Max Range: 3.8906. Min Range: -3.8906

Max Act: 3.2956. Min Act: -0.0000

Data Index: 230431 (The Pile)

Max Activating Token Index: 381

Text #7

Max Range: 3.8906. Min Range: -3.8906

Max Act: 3.1084. Min Act: -0.0000

Data Index: 292437 (The Pile)

Max Activating Token Index: 284

Text #8

Max Range: 3.8906. Min Range: -3.8906

Max Act: 3.2498. Min Act: -0.0000

Data Index: 735675 (The Pile)

Max Activating Token Index: 557

Text #9

Max Range: 3.8906. Min Range: -3.8906

Max Act: 3.3465. Min Act: -0.0000

Data Index: 151794 (The Pile)

Max Activating Token Index: 426

Text #10

Max Range: 3.8906. Min Range: -3.8906

Max Act: 3.3787. Min Act: -0.0000

Data Index: 1623135 (The Pile)

Max Activating Token Index: 112

Text #11

Max Range: 3.8906. Min Range: -3.8906

Max Act: 3.1608. Min Act: -0.0000

Data Index: 1498108 (The Pile)

Max Activating Token Index: 194

Text #12

Max Range: 3.8906. Min Range: -3.8906

Max Act: 3.3082. Min Act: -0.0000

Data Index: 178166 (The Pile)

Max Activating Token Index: 530

Text #13

Max Range: 3.8906. Min Range: -3.8906

Max Act: 3.2877. Min Act: -0.0000

Data Index: 821533 (The Pile)

Max Activating Token Index: 299

Text #14

Max Range: 3.8906. Min Range: -3.8906

Max Act: 3.2701. Min Act: -0.0000

Data Index: 1767894 (The Pile)

Max Activating Token Index: 518

Text #15

Max Range: 3.8906. Min Range: -3.8906

Max Act: 3.0024. Min Act: -0.0000

Data Index: 369936 (The Pile)

Max Activating Token Index: 987

Text #16

Max Range: 3.8906. Min Range: -3.8906

Max Act: 3.0959. Min Act: -0.0000

Data Index: 698027 (The Pile)

Max Activating Token Index: 798

Text #17

Max Range: 3.8906. Min Range: -3.8906

Max Act: 3.2801. Min Act: -0.0000

Data Index: 1748009 (The Pile)

Max Activating Token Index: 954

Text #18

Max Range: 3.8906. Min Range: -3.8906

Max Act: 3.1535. Min Act: -0.0000

Data Index: 562648 (The Pile)

Max Activating Token Index: 824

Text #19

Max Range: 3.8906. Min Range: -3.8906

Max Act: 3.0651. Min Act: -0.0000

Data Index: 20010 (The Pile)

Max Activating Token Index: 191