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

Dataset: The Pile

Neuron 3474 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7586. Min Range: -0.7586

Max Act: 0.7586. Min Act: -0.0000

Data Index: 816421 (The Pile)

Max Activating Token Index: 805

Text #1

Max Range: 0.7586. Min Range: -0.7586

Max Act: 0.7506. Min Act: -0.0000

Data Index: 1733562 (The Pile)

Max Activating Token Index: 69

Text #2

Max Range: 0.7586. Min Range: -0.7586

Max Act: 0.7122. Min Act: -0.0000

Data Index: 1113616 (The Pile)

Max Activating Token Index: 884

Text #3

Max Range: 0.7586. Min Range: -0.7586

Max Act: 0.6996. Min Act: -0.0000

Data Index: 1250855 (The Pile)

Max Activating Token Index: 100

Text #4

Max Range: 0.7586. Min Range: -0.7586

Max Act: 0.5978. Min Act: -0.0000

Data Index: 1504747 (The Pile)

Max Activating Token Index: 49

Text #5

Max Range: 0.7586. Min Range: -0.7586

Max Act: 0.6224. Min Act: -0.0000

Data Index: 81901 (The Pile)

Max Activating Token Index: 985

Text #6

Max Range: 0.7586. Min Range: -0.7586

Max Act: 0.6385. Min Act: -0.0000

Data Index: 364749 (The Pile)

Max Activating Token Index: 83

Text #7

Max Range: 0.7586. Min Range: -0.7586

Max Act: 0.5517. Min Act: -0.0000

Data Index: 829203 (The Pile)

Max Activating Token Index: 626

Text #8

Max Range: 0.7586. Min Range: -0.7586

Max Act: 0.6389. Min Act: -0.0000

Data Index: 978271 (The Pile)

Max Activating Token Index: 1016

Text #9

Max Range: 0.7586. Min Range: -0.7586

Max Act: 0.6005. Min Act: -0.0000

Data Index: 1778219 (The Pile)

Max Activating Token Index: 635

Text #10

Max Range: 0.7586. Min Range: -0.7586

Max Act: 0.5801. Min Act: -0.0000

Data Index: 1358882 (The Pile)

Max Activating Token Index: 47

Text #11

Max Range: 0.7586. Min Range: -0.7586

Max Act: 0.5799. Min Act: -0.0000

Data Index: 613074 (The Pile)

Max Activating Token Index: 66

Text #12

Max Range: 0.7586. Min Range: -0.7586

Max Act: 0.5714. Min Act: -0.0000

Data Index: 1113859 (The Pile)

Max Activating Token Index: 36

Text #13

Max Range: 0.7586. Min Range: -0.7586

Max Act: 0.5543. Min Act: -0.0000

Data Index: 1366632 (The Pile)

Max Activating Token Index: 781

Text #14

Max Range: 0.7586. Min Range: -0.7586

Max Act: 0.5488. Min Act: -0.0000

Data Index: 357837 (The Pile)

Max Activating Token Index: 140

Text #15

Max Range: 0.7586. Min Range: -0.7586

Max Act: 0.6307. Min Act: -0.0000

Data Index: 1390383 (The Pile)

Max Activating Token Index: 389

Text #16

Max Range: 0.7586. Min Range: -0.7586

Max Act: 0.5728. Min Act: -0.0000

Data Index: 1033456 (The Pile)

Max Activating Token Index: 65

Text #17

Max Range: 0.7586. Min Range: -0.7586

Max Act: 0.5902. Min Act: -0.0000

Data Index: 1622717 (The Pile)

Max Activating Token Index: 745

Text #18

Max Range: 0.7586. Min Range: -0.7586

Max Act: 0.6074. Min Act: -0.0000

Data Index: 811710 (The Pile)

Max Activating Token Index: 16

Text #19

Max Range: 0.7586. Min Range: -0.7586

Max Act: 0.5439. Min Act: -0.0000

Data Index: 877811 (The Pile)

Max Activating Token Index: 66