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

Dataset: The Pile

Neuron 1274 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.6967. Min Range: -5.6967

Max Act: 5.6967. Min Act: -0.0000

Data Index: 1026001 (The Pile)

Max Activating Token Index: 653

Text #1

Max Range: 5.6967. Min Range: -5.6967

Max Act: 5.4103. Min Act: -0.0000

Data Index: 276455 (The Pile)

Max Activating Token Index: 880

Text #2

Max Range: 5.6967. Min Range: -5.6967

Max Act: 4.6935. Min Act: -0.0000

Data Index: 1392019 (The Pile)

Max Activating Token Index: 600

Text #3

Max Range: 5.6967. Min Range: -5.6967

Max Act: 4.6453. Min Act: -0.0000

Data Index: 1950530 (The Pile)

Max Activating Token Index: 622

Text #4

Max Range: 5.6967. Min Range: -5.6967

Max Act: 4.5277. Min Act: -0.0000

Data Index: 620810 (The Pile)

Max Activating Token Index: 328

Text #5

Max Range: 5.6967. Min Range: -5.6967

Max Act: 4.2207. Min Act: -0.0000

Data Index: 1309594 (The Pile)

Max Activating Token Index: 664

Text #6

Max Range: 5.6967. Min Range: -5.6967

Max Act: 4.1348. Min Act: -0.0000

Data Index: 20738 (The Pile)

Max Activating Token Index: 531

Text #7

Max Range: 5.6967. Min Range: -5.6967

Max Act: 4.6112. Min Act: -0.0000

Data Index: 1683035 (The Pile)

Max Activating Token Index: 636

Text #8

Max Range: 5.6967. Min Range: -5.6967

Max Act: 4.6510. Min Act: -0.0000

Data Index: 1437037 (The Pile)

Max Activating Token Index: 853

Text #9

Max Range: 5.6967. Min Range: -5.6967

Max Act: 4.0960. Min Act: -0.0000

Data Index: 285556 (The Pile)

Max Activating Token Index: 474

Text #10

Max Range: 5.6967. Min Range: -5.6967

Max Act: 4.2505. Min Act: -0.0000

Data Index: 1821637 (The Pile)

Max Activating Token Index: 377

Text #11

Max Range: 5.6967. Min Range: -5.6967

Max Act: 4.0787. Min Act: -0.0000

Data Index: 1181456 (The Pile)

Max Activating Token Index: 292

Text #12

Max Range: 5.6967. Min Range: -5.6967

Max Act: 4.1636. Min Act: -0.0000

Data Index: 1297521 (The Pile)

Max Activating Token Index: 516

Text #13

Max Range: 5.6967. Min Range: -5.6967

Max Act: 3.9994. Min Act: -0.0000

Data Index: 579140 (The Pile)

Max Activating Token Index: 663

Text #14

Max Range: 5.6967. Min Range: -5.6967

Max Act: 4.1802. Min Act: -0.0000

Data Index: 990245 (The Pile)

Max Activating Token Index: 528

Text #15

Max Range: 5.6967. Min Range: -5.6967

Max Act: 3.8464. Min Act: -0.0000

Data Index: 1967081 (The Pile)

Max Activating Token Index: 826

Text #16

Max Range: 5.6967. Min Range: -5.6967

Max Act: 4.1203. Min Act: -0.0000

Data Index: 1467698 (The Pile)

Max Activating Token Index: 650

Text #17

Max Range: 5.6967. Min Range: -5.6967

Max Act: 4.2814. Min Act: -0.0000

Data Index: 1127812 (The Pile)

Max Activating Token Index: 456

Text #18

Max Range: 5.6967. Min Range: -5.6967

Max Act: 4.1519. Min Act: -0.0000

Data Index: 480619 (The Pile)

Max Activating Token Index: 745

Text #19

Max Range: 5.6967. Min Range: -5.6967

Max Act: 3.9176. Min Act: -0.0000

Data Index: 818302 (The Pile)

Max Activating Token Index: 565