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

Dataset: The Pile

Neuron 2421 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.8816. Min Range: -0.8816

Max Act: 0.8816. Min Act: -0.0000

Data Index: 826282 (The Pile)

Max Activating Token Index: 51

Text #1

Max Range: 0.8816. Min Range: -0.8816

Max Act: 0.8222. Min Act: -0.0000

Data Index: 1575925 (The Pile)

Max Activating Token Index: 876

Text #2

Max Range: 0.8816. Min Range: -0.8816

Max Act: 0.8280. Min Act: -0.0000

Data Index: 325026 (The Pile)

Max Activating Token Index: 501

Text #3

Max Range: 0.8816. Min Range: -0.8816

Max Act: 0.8397. Min Act: -0.0000

Data Index: 422414 (The Pile)

Max Activating Token Index: 275

Text #4

Max Range: 0.8816. Min Range: -0.8816

Max Act: 0.7377. Min Act: -0.0000

Data Index: 1449280 (The Pile)

Max Activating Token Index: 560

Text #5

Max Range: 0.8816. Min Range: -0.8816

Max Act: 0.7691. Min Act: -0.0000

Data Index: 840677 (The Pile)

Max Activating Token Index: 447

Text #6

Max Range: 0.8816. Min Range: -0.8816

Max Act: 0.7423. Min Act: -0.0000

Data Index: 563293 (The Pile)

Max Activating Token Index: 841

Text #7

Max Range: 0.8816. Min Range: -0.8816

Max Act: 0.7328. Min Act: -0.0000

Data Index: 57914 (The Pile)

Max Activating Token Index: 848

Text #8

Max Range: 0.8816. Min Range: -0.8816

Max Act: 0.7287. Min Act: -0.0000

Data Index: 571212 (The Pile)

Max Activating Token Index: 517

Text #9

Max Range: 0.8816. Min Range: -0.8816

Max Act: 0.7277. Min Act: -0.0000

Data Index: 1439906 (The Pile)

Max Activating Token Index: 644

Text #10

Max Range: 0.8816. Min Range: -0.8816

Max Act: 0.7232. Min Act: -0.0000

Data Index: 974851 (The Pile)

Max Activating Token Index: 747

Text #11

Max Range: 0.8816. Min Range: -0.8816

Max Act: 0.7299. Min Act: -0.0000

Data Index: 358237 (The Pile)

Max Activating Token Index: 18

Text #12

Max Range: 0.8816. Min Range: -0.8816

Max Act: 0.6590. Min Act: -0.0000

Data Index: 420279 (The Pile)

Max Activating Token Index: 771

Text #13

Max Range: 0.8816. Min Range: -0.8816

Max Act: 0.6444. Min Act: 0.0000

Data Index: 1036165 (The Pile)

Max Activating Token Index: 759

Text #14

Max Range: 0.8816. Min Range: -0.8816

Max Act: 0.6714. Min Act: -0.0000

Data Index: 1867773 (The Pile)

Max Activating Token Index: 235

Text #15

Max Range: 0.8816. Min Range: -0.8816

Max Act: 0.6723. Min Act: -0.0000

Data Index: 259471 (The Pile)

Max Activating Token Index: 460

Text #16

Max Range: 0.8816. Min Range: -0.8816

Max Act: 0.6247. Min Act: -0.0000

Data Index: 1007983 (The Pile)

Max Activating Token Index: 917

Text #17

Max Range: 0.8816. Min Range: -0.8816

Max Act: 0.6558. Min Act: -0.0000

Data Index: 1810233 (The Pile)

Max Activating Token Index: 292

Text #18

Max Range: 0.8816. Min Range: -0.8816

Max Act: 0.6499. Min Act: -0.0000

Data Index: 865493 (The Pile)

Max Activating Token Index: 137

Text #19

Max Range: 0.8816. Min Range: -0.8816

Max Act: 0.6617. Min Act: -0.0000

Data Index: 1447765 (The Pile)

Max Activating Token Index: 1011