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

Dataset: The Pile

Neuron 2907 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: 0.4430. Min Range: -0.4430

Max Act: 0.4123. Min Act: -0.0000

Data Index: 65229 (The Pile)

Max Activating Token Index: 155

Text #1

Max Range: 0.4430. Min Range: -0.4430

Max Act: 0.4190. Min Act: -0.0000

Data Index: 778690 (The Pile)

Max Activating Token Index: 1015

Text #2

Max Range: 0.4430. Min Range: -0.4430

Max Act: 0.4430. Min Act: -0.0000

Data Index: 1365313 (The Pile)

Max Activating Token Index: 884

Text #3

Max Range: 0.4430. Min Range: -0.4430

Max Act: 0.3760. Min Act: -0.0000

Data Index: 1968332 (The Pile)

Max Activating Token Index: 161

Text #4

Max Range: 0.4430. Min Range: -0.4430

Max Act: 0.3894. Min Act: -0.0000

Data Index: 956888 (The Pile)

Max Activating Token Index: 152

Text #5

Max Range: 0.4430. Min Range: -0.4430

Max Act: 0.3612. Min Act: -0.0000

Data Index: 1155347 (The Pile)

Max Activating Token Index: 511

Text #6

Max Range: 0.4430. Min Range: -0.4430

Max Act: 0.4005. Min Act: -0.0000

Data Index: 1724246 (The Pile)

Max Activating Token Index: 639

Text #7

Max Range: 0.4430. Min Range: -0.4430

Max Act: 0.3763. Min Act: -0.0000

Data Index: 256686 (The Pile)

Max Activating Token Index: 70

Text #8

Max Range: 0.4430. Min Range: -0.4430

Max Act: 0.3563. Min Act: -0.0000

Data Index: 1123814 (The Pile)

Max Activating Token Index: 558

Text #9

Max Range: 0.4430. Min Range: -0.4430

Max Act: 0.3554. Min Act: -0.0000

Data Index: 453133 (The Pile)

Max Activating Token Index: 207

Text #10

Max Range: 0.4430. Min Range: -0.4430

Max Act: 0.3287. Min Act: -0.0000

Data Index: 202883 (The Pile)

Max Activating Token Index: 377

Text #11

Max Range: 0.4430. Min Range: -0.4430

Max Act: 0.3626. Min Act: -0.0000

Data Index: 139210 (The Pile)

Max Activating Token Index: 108

Text #12

Max Range: 0.4430. Min Range: -0.4430

Max Act: 0.3597. Min Act: -0.0000

Data Index: 1214972 (The Pile)

Max Activating Token Index: 647

Text #13

Max Range: 0.4430. Min Range: -0.4430

Max Act: 0.3241. Min Act: -0.0000

Data Index: 104701 (The Pile)

Max Activating Token Index: 600

Text #14

Max Range: 0.4430. Min Range: -0.4430

Max Act: 0.3380. Min Act: -0.0000

Data Index: 1131325 (The Pile)

Max Activating Token Index: 115

Text #15

Max Range: 0.4430. Min Range: -0.4430

Max Act: 0.3396. Min Act: -0.0000

Data Index: 392626 (The Pile)

Max Activating Token Index: 390

Text #16

Max Range: 0.4430. Min Range: -0.4430

Max Act: 0.3238. Min Act: -0.0000

Data Index: 1501771 (The Pile)

Max Activating Token Index: 583

Text #17

Max Range: 0.4430. Min Range: -0.4430

Max Act: 0.3045. Min Act: -0.0000

Data Index: 1617616 (The Pile)

Max Activating Token Index: 311

Text #18

Max Range: 0.4430. Min Range: -0.4430

Max Act: 0.3250. Min Act: -0.0000

Data Index: 858344 (The Pile)

Max Activating Token Index: 974

Text #19

Max Range: 0.4430. Min Range: -0.4430

Max Act: 0.3375. Min Act: -0.0000

Data Index: 1399521 (The Pile)

Max Activating Token Index: 710