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

Dataset: The Pile

Neuron 3797 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4410. Min Range: -1.4410

Max Act: 1.2626. Min Act: -0.0000

Data Index: 417779 (The Pile)

Max Activating Token Index: 971

Text #1

Max Range: 1.4410. Min Range: -1.4410

Max Act: 1.4410. Min Act: -0.0000

Data Index: 1866045 (The Pile)

Max Activating Token Index: 717

Text #2

Max Range: 1.4410. Min Range: -1.4410

Max Act: 1.1125. Min Act: -0.0000

Data Index: 592486 (The Pile)

Max Activating Token Index: 1001

Text #3

Max Range: 1.4410. Min Range: -1.4410

Max Act: 1.3034. Min Act: -0.0000

Data Index: 1696352 (The Pile)

Max Activating Token Index: 807

Text #4

Max Range: 1.4410. Min Range: -1.4410

Max Act: 1.2231. Min Act: -0.0000

Data Index: 1088628 (The Pile)

Max Activating Token Index: 451

Text #5

Max Range: 1.4410. Min Range: -1.4410

Max Act: 1.1015. Min Act: -0.0000

Data Index: 66294 (The Pile)

Max Activating Token Index: 845

Text #6

Max Range: 1.4410. Min Range: -1.4410

Max Act: 1.2727. Min Act: -0.0000

Data Index: 1864632 (The Pile)

Max Activating Token Index: 764

Text #7

Max Range: 1.4410. Min Range: -1.4410

Max Act: 1.3248. Min Act: -0.0000

Data Index: 1992383 (The Pile)

Max Activating Token Index: 105

Text #8

Max Range: 1.4410. Min Range: -1.4410

Max Act: 1.2118. Min Act: -0.0000

Data Index: 823148 (The Pile)

Max Activating Token Index: 951

Text #9

Max Range: 1.4410. Min Range: -1.4410

Max Act: 1.2006. Min Act: -0.0000

Data Index: 811695 (The Pile)

Max Activating Token Index: 134

Text #10

Max Range: 1.4410. Min Range: -1.4410

Max Act: 1.2674. Min Act: -0.0000

Data Index: 829258 (The Pile)

Max Activating Token Index: 248

Text #11

Max Range: 1.4410. Min Range: -1.4410

Max Act: 1.2048. Min Act: -0.0000

Data Index: 1367697 (The Pile)

Max Activating Token Index: 141

Text #12

Max Range: 1.4410. Min Range: -1.4410

Max Act: 1.3423. Min Act: -0.0000

Data Index: 377603 (The Pile)

Max Activating Token Index: 84

Text #13

Max Range: 1.4410. Min Range: -1.4410

Max Act: 1.1548. Min Act: -0.0000

Data Index: 382601 (The Pile)

Max Activating Token Index: 879

Text #14

Max Range: 1.4410. Min Range: -1.4410

Max Act: 1.1979. Min Act: -0.0000

Data Index: 1501358 (The Pile)

Max Activating Token Index: 46

Text #15

Max Range: 1.4410. Min Range: -1.4410

Max Act: 1.1907. Min Act: -0.0000

Data Index: 1550869 (The Pile)

Max Activating Token Index: 934

Text #16

Max Range: 1.4410. Min Range: -1.4410

Max Act: 1.1831. Min Act: -0.0000

Data Index: 1641053 (The Pile)

Max Activating Token Index: 314

Text #17

Max Range: 1.4410. Min Range: -1.4410

Max Act: 1.2876. Min Act: -0.0000

Data Index: 1302298 (The Pile)

Max Activating Token Index: 129

Text #18

Max Range: 1.4410. Min Range: -1.4410

Max Act: 1.2524. Min Act: -0.0000

Data Index: 1345323 (The Pile)

Max Activating Token Index: 116

Text #19

Max Range: 1.4410. Min Range: -1.4410

Max Act: 1.1723. Min Act: -0.0000

Data Index: 101598 (The Pile)

Max Activating Token Index: 460