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

Dataset: The Pile

Neuron 1201 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: 0.6804. Min Range: -0.6804

Max Act: 0.6804. Min Act: -0.0000

Data Index: 628293 (The Pile)

Max Activating Token Index: 497

Text #1

Max Range: 0.6804. Min Range: -0.6804

Max Act: 0.6577. Min Act: -0.0000

Data Index: 1659694 (The Pile)

Max Activating Token Index: 534

Text #2

Max Range: 0.6804. Min Range: -0.6804

Max Act: 0.6369. Min Act: -0.0000

Data Index: 672533 (The Pile)

Max Activating Token Index: 626

Text #3

Max Range: 0.6804. Min Range: -0.6804

Max Act: 0.5944. Min Act: -0.0000

Data Index: 361114 (The Pile)

Max Activating Token Index: 724

Text #4

Max Range: 0.6804. Min Range: -0.6804

Max Act: 0.6232. Min Act: -0.0000

Data Index: 115075 (The Pile)

Max Activating Token Index: 546

Text #5

Max Range: 0.6804. Min Range: -0.6804

Max Act: 0.5277. Min Act: -0.0000

Data Index: 704366 (The Pile)

Max Activating Token Index: 111

Text #6

Max Range: 0.6804. Min Range: -0.6804

Max Act: 0.5677. Min Act: -0.0000

Data Index: 899628 (The Pile)

Max Activating Token Index: 759

Text #7

Max Range: 0.6804. Min Range: -0.6804

Max Act: 0.5476. Min Act: -0.0000

Data Index: 730694 (The Pile)

Max Activating Token Index: 734

Text #8

Max Range: 0.6804. Min Range: -0.6804

Max Act: 0.5727. Min Act: -0.0000

Data Index: 1474936 (The Pile)

Max Activating Token Index: 848

Text #9

Max Range: 0.6804. Min Range: -0.6804

Max Act: 0.5146. Min Act: -0.0000

Data Index: 1667623 (The Pile)

Max Activating Token Index: 486

Text #10

Max Range: 0.6804. Min Range: -0.6804

Max Act: 0.5262. Min Act: -0.0000

Data Index: 1454017 (The Pile)

Max Activating Token Index: 652

Text #11

Max Range: 0.6804. Min Range: -0.6804

Max Act: 0.4819. Min Act: -0.0000

Data Index: 1582262 (The Pile)

Max Activating Token Index: 667

Text #12

Max Range: 0.6804. Min Range: -0.6804

Max Act: 0.5298. Min Act: -0.0000

Data Index: 28056 (The Pile)

Max Activating Token Index: 846

Text #13

Max Range: 0.6804. Min Range: -0.6804

Max Act: 0.5179. Min Act: -0.0000

Data Index: 1645289 (The Pile)

Max Activating Token Index: 719

Text #14

Max Range: 0.6804. Min Range: -0.6804

Max Act: 0.5202. Min Act: -0.0000

Data Index: 768111 (The Pile)

Max Activating Token Index: 456

Text #15

Max Range: 0.6804. Min Range: -0.6804

Max Act: 0.4656. Min Act: -0.0000

Data Index: 1083758 (The Pile)

Max Activating Token Index: 950

Text #16

Max Range: 0.6804. Min Range: -0.6804

Max Act: 0.4817. Min Act: -0.0000

Data Index: 1365099 (The Pile)

Max Activating Token Index: 774

Text #17

Max Range: 0.6804. Min Range: -0.6804

Max Act: 0.5049. Min Act: -0.0000

Data Index: 625212 (The Pile)

Max Activating Token Index: 267

Text #18

Max Range: 0.6804. Min Range: -0.6804

Max Act: 0.4862. Min Act: -0.0000

Data Index: 1481579 (The Pile)

Max Activating Token Index: 698

Text #19

Max Range: 0.6804. Min Range: -0.6804

Max Act: 0.5327. Min Act: -0.0000

Data Index: 1733773 (The Pile)

Max Activating Token Index: 862