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

Dataset: The Pile

Neuron 4449 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: 5.9856. Min Range: -5.9856

Max Act: 5.9856. Min Act: -0.0000

Data Index: 983305 (The Pile)

Max Activating Token Index: 312

Text #1

Max Range: 5.9856. Min Range: -5.9856

Max Act: 5.0728. Min Act: -0.0000

Data Index: 1951777 (The Pile)

Max Activating Token Index: 156

Text #2

Max Range: 5.9856. Min Range: -5.9856

Max Act: 4.9499. Min Act: -0.0000

Data Index: 271256 (The Pile)

Max Activating Token Index: 505

Text #3

Max Range: 5.9856. Min Range: -5.9856

Max Act: 5.2908. Min Act: -0.0000

Data Index: 884986 (The Pile)

Max Activating Token Index: 42

Text #4

Max Range: 5.9856. Min Range: -5.9856

Max Act: 4.3021. Min Act: -0.0000

Data Index: 1921303 (The Pile)

Max Activating Token Index: 622

Text #5

Max Range: 5.9856. Min Range: -5.9856

Max Act: 4.4661. Min Act: -0.0000

Data Index: 1625969 (The Pile)

Max Activating Token Index: 335

Text #6

Max Range: 5.9856. Min Range: -5.9856

Max Act: 4.4350. Min Act: -0.0000

Data Index: 842962 (The Pile)

Max Activating Token Index: 55

Text #7

Max Range: 5.9856. Min Range: -5.9856

Max Act: 3.5721. Min Act: -0.0000

Data Index: 1946090 (The Pile)

Max Activating Token Index: 586

Text #8

Max Range: 5.9856. Min Range: -5.9856

Max Act: 4.0281. Min Act: -0.0000

Data Index: 852065 (The Pile)

Max Activating Token Index: 765

Text #9

Max Range: 5.9856. Min Range: -5.9856

Max Act: 3.5411. Min Act: -0.0000

Data Index: 1384329 (The Pile)

Max Activating Token Index: 204

Text #10

Max Range: 5.9856. Min Range: -5.9856

Max Act: 3.4627. Min Act: -0.0000

Data Index: 1367423 (The Pile)

Max Activating Token Index: 749

Text #11

Max Range: 5.9856. Min Range: -5.9856

Max Act: 3.5480. Min Act: -0.0000

Data Index: 1212831 (The Pile)

Max Activating Token Index: 78

Text #12

Max Range: 5.9856. Min Range: -5.9856

Max Act: 3.3349. Min Act: -0.0000

Data Index: 512578 (The Pile)

Max Activating Token Index: 471

Text #13

Max Range: 5.9856. Min Range: -5.9856

Max Act: 2.5893. Min Act: -0.0000

Data Index: 1392040 (The Pile)

Max Activating Token Index: 834

Text #14

Max Range: 5.9856. Min Range: -5.9856

Max Act: 3.1661. Min Act: -0.0000

Data Index: 1587341 (The Pile)

Max Activating Token Index: 892

Text #15

Max Range: 5.9856. Min Range: -5.9856

Max Act: 3.3221. Min Act: -0.0000

Data Index: 1014933 (The Pile)

Max Activating Token Index: 672

Text #16

Max Range: 5.9856. Min Range: -5.9856

Max Act: 3.3851. Min Act: -0.0000

Data Index: 1978285 (The Pile)

Max Activating Token Index: 270

Text #17

Max Range: 5.9856. Min Range: -5.9856

Max Act: 3.5020. Min Act: -0.0000

Data Index: 580752 (The Pile)

Max Activating Token Index: 490

Text #18

Max Range: 5.9856. Min Range: -5.9856

Max Act: 2.7145. Min Act: -0.0000

Data Index: 1685797 (The Pile)

Max Activating Token Index: 628

Text #19

Max Range: 5.9856. Min Range: -5.9856

Max Act: 3.1592. Min Act: -0.0000

Data Index: 1505134 (The Pile)

Max Activating Token Index: 948