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

Dataset: The Pile

Neuron 3585 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: 0.8764. Min Range: -0.8764

Max Act: 0.8474. Min Act: -0.0000

Data Index: 384896 (The Pile)

Max Activating Token Index: 982

Text #1

Max Range: 0.8764. Min Range: -0.8764

Max Act: 0.8764. Min Act: -0.0000

Data Index: 1682738 (The Pile)

Max Activating Token Index: 950

Text #2

Max Range: 0.8764. Min Range: -0.8764

Max Act: 0.7930. Min Act: 0.0000

Data Index: 90832 (The Pile)

Max Activating Token Index: 46

Text #3

Max Range: 0.8764. Min Range: -0.8764

Max Act: 0.7325. Min Act: -0.0000

Data Index: 1124020 (The Pile)

Max Activating Token Index: 767

Text #4

Max Range: 0.8764. Min Range: -0.8764

Max Act: 0.7761. Min Act: -0.0000

Data Index: 1561718 (The Pile)

Max Activating Token Index: 1012

Text #5

Max Range: 0.8764. Min Range: -0.8764

Max Act: 0.7147. Min Act: -0.0000

Data Index: 1577473 (The Pile)

Max Activating Token Index: 754

Text #6

Max Range: 0.8764. Min Range: -0.8764

Max Act: 0.7249. Min Act: -0.0000

Data Index: 449833 (The Pile)

Max Activating Token Index: 851

Text #7

Max Range: 0.8764. Min Range: -0.8764

Max Act: 0.6925. Min Act: -0.0000

Data Index: 1750996 (The Pile)

Max Activating Token Index: 776

Text #8

Max Range: 0.8764. Min Range: -0.8764

Max Act: 0.7305. Min Act: -0.0000

Data Index: 1993814 (The Pile)

Max Activating Token Index: 363

Text #9

Max Range: 0.8764. Min Range: -0.8764

Max Act: 0.6815. Min Act: 0.0000

Data Index: 578537 (The Pile)

Max Activating Token Index: 903

Text #10

Max Range: 0.8764. Min Range: -0.8764

Max Act: 0.6946. Min Act: 0.0000

Data Index: 1604846 (The Pile)

Max Activating Token Index: 98

Text #11

Max Range: 0.8764. Min Range: -0.8764

Max Act: 0.6639. Min Act: -0.0000

Data Index: 817132 (The Pile)

Max Activating Token Index: 631

Text #12

Max Range: 0.8764. Min Range: -0.8764

Max Act: 0.6652. Min Act: -0.0000

Data Index: 1050977 (The Pile)

Max Activating Token Index: 866

Text #13

Max Range: 0.8764. Min Range: -0.8764

Max Act: 0.6164. Min Act: -0.0000

Data Index: 842865 (The Pile)

Max Activating Token Index: 812

Text #14

Max Range: 0.8764. Min Range: -0.8764

Max Act: 0.5447. Min Act: -0.0000

Data Index: 1525795 (The Pile)

Max Activating Token Index: 570

Text #15

Max Range: 0.8764. Min Range: -0.8764

Max Act: 0.6304. Min Act: -0.0000

Data Index: 1730079 (The Pile)

Max Activating Token Index: 78

Text #16

Max Range: 0.8764. Min Range: -0.8764

Max Act: 0.6106. Min Act: -0.0000

Data Index: 356240 (The Pile)

Max Activating Token Index: 227

Text #17

Max Range: 0.8764. Min Range: -0.8764

Max Act: 0.6345. Min Act: -0.0000

Data Index: 1148493 (The Pile)

Max Activating Token Index: 883

Text #18

Max Range: 0.8764. Min Range: -0.8764

Max Act: 0.6156. Min Act: -0.0000

Data Index: 1339904 (The Pile)

Max Activating Token Index: 702

Text #19

Max Range: 0.8764. Min Range: -0.8764

Max Act: 0.5507. Min Act: -0.0000

Data Index: 1951113 (The Pile)

Max Activating Token Index: 808