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

Dataset: The Pile

Neuron 2577 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: 3.0722. Min Range: -3.0722

Max Act: 3.0722. Min Act: -0.0000

Data Index: 1779035 (The Pile)

Max Activating Token Index: 592

Text #1

Max Range: 3.0722. Min Range: -3.0722

Max Act: 2.9398. Min Act: -0.0000

Data Index: 1319231 (The Pile)

Max Activating Token Index: 403

Text #2

Max Range: 3.0722. Min Range: -3.0722

Max Act: 2.6768. Min Act: -0.0000

Data Index: 1630548 (The Pile)

Max Activating Token Index: 399

Text #3

Max Range: 3.0722. Min Range: -3.0722

Max Act: 2.5391. Min Act: -0.0000

Data Index: 942938 (The Pile)

Max Activating Token Index: 675

Text #4

Max Range: 3.0722. Min Range: -3.0722

Max Act: 2.5649. Min Act: -0.0000

Data Index: 1733896 (The Pile)

Max Activating Token Index: 972

Text #5

Max Range: 3.0722. Min Range: -3.0722

Max Act: 2.4620. Min Act: -0.0000

Data Index: 152358 (The Pile)

Max Activating Token Index: 333

Text #6

Max Range: 3.0722. Min Range: -3.0722

Max Act: 2.3455. Min Act: -0.0000

Data Index: 635269 (The Pile)

Max Activating Token Index: 363

Text #7

Max Range: 3.0722. Min Range: -3.0722

Max Act: 2.3123. Min Act: -0.0000

Data Index: 182315 (The Pile)

Max Activating Token Index: 302

Text #8

Max Range: 3.0722. Min Range: -3.0722

Max Act: 2.4422. Min Act: -0.0000

Data Index: 1048402 (The Pile)

Max Activating Token Index: 297

Text #9

Max Range: 3.0722. Min Range: -3.0722

Max Act: 2.2769. Min Act: -0.0000

Data Index: 1744846 (The Pile)

Max Activating Token Index: 223

Text #10

Max Range: 3.0722. Min Range: -3.0722

Max Act: 2.3874. Min Act: -0.0000

Data Index: 1075683 (The Pile)

Max Activating Token Index: 582

Text #11

Max Range: 3.0722. Min Range: -3.0722

Max Act: 2.2496. Min Act: -0.0000

Data Index: 1487364 (The Pile)

Max Activating Token Index: 982

Text #12

Max Range: 3.0722. Min Range: -3.0722

Max Act: 2.2246. Min Act: -0.0000

Data Index: 1230390 (The Pile)

Max Activating Token Index: 180

Text #13

Max Range: 3.0722. Min Range: -3.0722

Max Act: 2.4402. Min Act: -0.0000

Data Index: 320795 (The Pile)

Max Activating Token Index: 162

Text #14

Max Range: 3.0722. Min Range: -3.0722

Max Act: 2.3147. Min Act: -0.0000

Data Index: 918966 (The Pile)

Max Activating Token Index: 824

Text #15

Max Range: 3.0722. Min Range: -3.0722

Max Act: 2.1507. Min Act: -0.0000

Data Index: 1026523 (The Pile)

Max Activating Token Index: 905

Text #16

Max Range: 3.0722. Min Range: -3.0722

Max Act: 2.4633. Min Act: -0.0000

Data Index: 1412976 (The Pile)

Max Activating Token Index: 902

Text #17

Max Range: 3.0722. Min Range: -3.0722

Max Act: 2.3589. Min Act: -0.0000

Data Index: 420329 (The Pile)

Max Activating Token Index: 296

Text #18

Max Range: 3.0722. Min Range: -3.0722

Max Act: 2.2487. Min Act: -0.0000

Data Index: 1843893 (The Pile)

Max Activating Token Index: 185

Text #19

Max Range: 3.0722. Min Range: -3.0722

Max Act: 2.3564. Min Act: -0.0000

Data Index: 1543743 (The Pile)

Max Activating Token Index: 383