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

Dataset: The Pile

Neuron 3734 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: 1.5369. Min Range: -1.5369

Max Act: 1.4683. Min Act: -0.0000

Data Index: 1342122 (The Pile)

Max Activating Token Index: 70

Text #1

Max Range: 1.5369. Min Range: -1.5369

Max Act: 1.5369. Min Act: -0.0000

Data Index: 823244 (The Pile)

Max Activating Token Index: 587

Text #2

Max Range: 1.5369. Min Range: -1.5369

Max Act: 1.4992. Min Act: -0.0000

Data Index: 1486562 (The Pile)

Max Activating Token Index: 124

Text #3

Max Range: 1.5369. Min Range: -1.5369

Max Act: 1.4503. Min Act: -0.0000

Data Index: 1926214 (The Pile)

Max Activating Token Index: 710

Text #4

Max Range: 1.5369. Min Range: -1.5369

Max Act: 1.2893. Min Act: -0.0000

Data Index: 675104 (The Pile)

Max Activating Token Index: 811

Text #5

Max Range: 1.5369. Min Range: -1.5369

Max Act: 1.3617. Min Act: -0.0000

Data Index: 935134 (The Pile)

Max Activating Token Index: 490

Text #6

Max Range: 1.5369. Min Range: -1.5369

Max Act: 1.3350. Min Act: -0.0000

Data Index: 1458253 (The Pile)

Max Activating Token Index: 222

Text #7

Max Range: 1.5369. Min Range: -1.5369

Max Act: 1.4074. Min Act: -0.0000

Data Index: 1712919 (The Pile)

Max Activating Token Index: 597

Text #8

Max Range: 1.5369. Min Range: -1.5369

Max Act: 1.3980. Min Act: -0.0000

Data Index: 420868 (The Pile)

Max Activating Token Index: 412

Text #9

Max Range: 1.5369. Min Range: -1.5369

Max Act: 1.2801. Min Act: -0.0000

Data Index: 283469 (The Pile)

Max Activating Token Index: 62

Text #10

Max Range: 1.5369. Min Range: -1.5369

Max Act: 1.1966. Min Act: -0.0000

Data Index: 343919 (The Pile)

Max Activating Token Index: 814

Text #11

Max Range: 1.5369. Min Range: -1.5369

Max Act: 1.2486. Min Act: -0.0000

Data Index: 580511 (The Pile)

Max Activating Token Index: 629

Text #12

Max Range: 1.5369. Min Range: -1.5369

Max Act: 1.2986. Min Act: -0.0000

Data Index: 143516 (The Pile)

Max Activating Token Index: 736

Text #13

Max Range: 1.5369. Min Range: -1.5369

Max Act: 1.2840. Min Act: -0.0000

Data Index: 62837 (The Pile)

Max Activating Token Index: 135

Text #14

Max Range: 1.5369. Min Range: -1.5369

Max Act: 1.2002. Min Act: -0.0000

Data Index: 833108 (The Pile)

Max Activating Token Index: 289

Text #15

Max Range: 1.5369. Min Range: -1.5369

Max Act: 1.1840. Min Act: -0.0000

Data Index: 301908 (The Pile)

Max Activating Token Index: 83

Text #16

Max Range: 1.5369. Min Range: -1.5369

Max Act: 1.1784. Min Act: -0.0000

Data Index: 1064472 (The Pile)

Max Activating Token Index: 277

Text #17

Max Range: 1.5369. Min Range: -1.5369

Max Act: 1.1789. Min Act: -0.0000

Data Index: 1631983 (The Pile)

Max Activating Token Index: 615

Text #18

Max Range: 1.5369. Min Range: -1.5369

Max Act: 1.1615. Min Act: -0.0000

Data Index: 237583 (The Pile)

Max Activating Token Index: 404

Text #19

Max Range: 1.5369. Min Range: -1.5369

Max Act: 1.0941. Min Act: -0.0000

Data Index: 1180614 (The Pile)

Max Activating Token Index: 423