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

Dataset: The Pile

Neuron 3517 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: 3.1985. Min Range: -3.1985

Max Act: 3.1985. Min Act: -0.0000

Data Index: 1538190 (The Pile)

Max Activating Token Index: 229

Text #1

Max Range: 3.1985. Min Range: -3.1985

Max Act: 2.5231. Min Act: -0.0000

Data Index: 549321 (The Pile)

Max Activating Token Index: 771

Text #2

Max Range: 3.1985. Min Range: -3.1985

Max Act: 2.3657. Min Act: -0.0000

Data Index: 86867 (The Pile)

Max Activating Token Index: 842

Text #3

Max Range: 3.1985. Min Range: -3.1985

Max Act: 2.3745. Min Act: -0.0000

Data Index: 1631377 (The Pile)

Max Activating Token Index: 520

Text #4

Max Range: 3.1985. Min Range: -3.1985

Max Act: 2.3670. Min Act: -0.0000

Data Index: 1347534 (The Pile)

Max Activating Token Index: 567

Text #5

Max Range: 3.1985. Min Range: -3.1985

Max Act: 2.5161. Min Act: -0.0000

Data Index: 1542128 (The Pile)

Max Activating Token Index: 136

Text #6

Max Range: 3.1985. Min Range: -3.1985

Max Act: 2.2041. Min Act: -0.0000

Data Index: 1477744 (The Pile)

Max Activating Token Index: 731

Text #7

Max Range: 3.1985. Min Range: -3.1985

Max Act: 2.4215. Min Act: -0.0000

Data Index: 736085 (The Pile)

Max Activating Token Index: 742

Text #8

Max Range: 3.1985. Min Range: -3.1985

Max Act: 2.3980. Min Act: -0.0000

Data Index: 667030 (The Pile)

Max Activating Token Index: 684

Text #9

Max Range: 3.1985. Min Range: -3.1985

Max Act: 2.2501. Min Act: -0.0000

Data Index: 1077264 (The Pile)

Max Activating Token Index: 977

Text #10

Max Range: 3.1985. Min Range: -3.1985

Max Act: 2.0612. Min Act: -0.0000

Data Index: 1374050 (The Pile)

Max Activating Token Index: 725

Text #11

Max Range: 3.1985. Min Range: -3.1985

Max Act: 2.1547. Min Act: -0.0000

Data Index: 1127749 (The Pile)

Max Activating Token Index: 486

Text #12

Max Range: 3.1985. Min Range: -3.1985

Max Act: 2.3226. Min Act: -0.0000

Data Index: 662295 (The Pile)

Max Activating Token Index: 540

Text #13

Max Range: 3.1985. Min Range: -3.1985

Max Act: 1.8404. Min Act: -0.0000

Data Index: 1654034 (The Pile)

Max Activating Token Index: 611

Text #14

Max Range: 3.1985. Min Range: -3.1985

Max Act: 2.0741. Min Act: -0.0000

Data Index: 580088 (The Pile)

Max Activating Token Index: 513

Text #15

Max Range: 3.1985. Min Range: -3.1985

Max Act: 1.9539. Min Act: -0.0000

Data Index: 1469374 (The Pile)

Max Activating Token Index: 487

Text #16

Max Range: 3.1985. Min Range: -3.1985

Max Act: 1.9536. Min Act: -0.0000

Data Index: 929928 (The Pile)

Max Activating Token Index: 911

Text #17

Max Range: 3.1985. Min Range: -3.1985

Max Act: 2.0354. Min Act: -0.0000

Data Index: 65354 (The Pile)

Max Activating Token Index: 104

Text #18

Max Range: 3.1985. Min Range: -3.1985

Max Act: 2.0820. Min Act: -0.0000

Data Index: 1658849 (The Pile)

Max Activating Token Index: 142

Text #19

Max Range: 3.1985. Min Range: -3.1985

Max Act: 1.7625. Min Act: -0.0000

Data Index: 954168 (The Pile)

Max Activating Token Index: 826