Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 2515 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.5853. Min Range: -0.5853

Max Act: 0.5853. Min Act: -0.0000

Data Index: 898843 (The Pile)

Max Activating Token Index: 490

Text #1

Max Range: 0.5853. Min Range: -0.5853

Max Act: 0.5004. Min Act: -0.0000

Data Index: 315650 (The Pile)

Max Activating Token Index: 880

Text #2

Max Range: 0.5853. Min Range: -0.5853

Max Act: 0.5424. Min Act: -0.0000

Data Index: 1854834 (The Pile)

Max Activating Token Index: 907

Text #3

Max Range: 0.5853. Min Range: -0.5853

Max Act: 0.4623. Min Act: -0.0000

Data Index: 1457887 (The Pile)

Max Activating Token Index: 240

Text #4

Max Range: 0.5853. Min Range: -0.5853

Max Act: 0.4796. Min Act: -0.0000

Data Index: 71910 (The Pile)

Max Activating Token Index: 109

Text #5

Max Range: 0.5853. Min Range: -0.5853

Max Act: 0.4794. Min Act: -0.0000

Data Index: 638151 (The Pile)

Max Activating Token Index: 311

Text #6

Max Range: 0.5853. Min Range: -0.5853

Max Act: 0.4508. Min Act: -0.0000

Data Index: 1143361 (The Pile)

Max Activating Token Index: 896

Text #7

Max Range: 0.5853. Min Range: -0.5853

Max Act: 0.4828. Min Act: -0.0000

Data Index: 1644189 (The Pile)

Max Activating Token Index: 633

Text #8

Max Range: 0.5853. Min Range: -0.5853

Max Act: 0.4577. Min Act: -0.0000

Data Index: 49640 (The Pile)

Max Activating Token Index: 131

Text #9

Max Range: 0.5853. Min Range: -0.5853

Max Act: 0.4887. Min Act: -0.0000

Data Index: 475477 (The Pile)

Max Activating Token Index: 730

Text #10

Max Range: 0.5853. Min Range: -0.5853

Max Act: 0.4234. Min Act: -0.0000

Data Index: 697761 (The Pile)

Max Activating Token Index: 983

Text #11

Max Range: 0.5853. Min Range: -0.5853

Max Act: 0.4208. Min Act: -0.0000

Data Index: 1295765 (The Pile)

Max Activating Token Index: 458

Text #12

Max Range: 0.5853. Min Range: -0.5853

Max Act: 0.4319. Min Act: -0.0000

Data Index: 465448 (The Pile)

Max Activating Token Index: 26

Text #13

Max Range: 0.5853. Min Range: -0.5853

Max Act: 0.4132. Min Act: -0.0000

Data Index: 1840844 (The Pile)

Max Activating Token Index: 98

Text #14

Max Range: 0.5853. Min Range: -0.5853

Max Act: 0.4140. Min Act: -0.0000

Data Index: 1780807 (The Pile)

Max Activating Token Index: 778

Text #15

Max Range: 0.5853. Min Range: -0.5853

Max Act: 0.4157. Min Act: -0.0000

Data Index: 343133 (The Pile)

Max Activating Token Index: 496

Text #16

Max Range: 0.5853. Min Range: -0.5853

Max Act: 0.4227. Min Act: -0.0000

Data Index: 1484320 (The Pile)

Max Activating Token Index: 571

Text #17

Max Range: 0.5853. Min Range: -0.5853

Max Act: 0.4329. Min Act: -0.0000

Data Index: 1042896 (The Pile)

Max Activating Token Index: 243

Text #18

Max Range: 0.5853. Min Range: -0.5853

Max Act: 0.4166. Min Act: -0.0000

Data Index: 1298512 (The Pile)

Max Activating Token Index: 714

Text #19

Max Range: 0.5853. Min Range: -0.5853

Max Act: 0.4291. Min Act: -0.0000

Data Index: 919240 (The Pile)

Max Activating Token Index: 963