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

Dataset: The Pile

Neuron 619 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: 0.6202. Min Range: -0.6202

Max Act: 0.6202. Min Act: -0.0000

Data Index: 1615510 (The Pile)

Max Activating Token Index: 992

Text #1

Max Range: 0.6202. Min Range: -0.6202

Max Act: 0.5865. Min Act: -0.0000

Data Index: 1739618 (The Pile)

Max Activating Token Index: 1023

Text #2

Max Range: 0.6202. Min Range: -0.6202

Max Act: 0.4769. Min Act: -0.0000

Data Index: 383345 (The Pile)

Max Activating Token Index: 988

Text #3

Max Range: 0.6202. Min Range: -0.6202

Max Act: 0.4855. Min Act: -0.0000

Data Index: 639085 (The Pile)

Max Activating Token Index: 14

Text #4

Max Range: 0.6202. Min Range: -0.6202

Max Act: 0.5260. Min Act: -0.0000

Data Index: 1398073 (The Pile)

Max Activating Token Index: 941

Text #5

Max Range: 0.6202. Min Range: -0.6202

Max Act: 0.4962. Min Act: -0.0000

Data Index: 1285905 (The Pile)

Max Activating Token Index: 903

Text #6

Max Range: 0.6202. Min Range: -0.6202

Max Act: 0.4732. Min Act: -0.0000

Data Index: 1780265 (The Pile)

Max Activating Token Index: 758

Text #7

Max Range: 0.6202. Min Range: -0.6202

Max Act: 0.4284. Min Act: -0.0000

Data Index: 1665208 (The Pile)

Max Activating Token Index: 816

Text #8

Max Range: 0.6202. Min Range: -0.6202

Max Act: 0.4298. Min Act: -0.0000

Data Index: 47321 (The Pile)

Max Activating Token Index: 977

Text #9

Max Range: 0.6202. Min Range: -0.6202

Max Act: 0.4454. Min Act: -0.0000

Data Index: 1911140 (The Pile)

Max Activating Token Index: 823

Text #10

Max Range: 0.6202. Min Range: -0.6202

Max Act: 0.4027. Min Act: -0.0000

Data Index: 1213688 (The Pile)

Max Activating Token Index: 715

Text #11

Max Range: 0.6202. Min Range: -0.6202

Max Act: 0.4012. Min Act: -0.0000

Data Index: 1551011 (The Pile)

Max Activating Token Index: 205

Text #12

Max Range: 0.6202. Min Range: -0.6202

Max Act: 0.3807. Min Act: -0.0000

Data Index: 333154 (The Pile)

Max Activating Token Index: 492

Text #13

Max Range: 0.6202. Min Range: -0.6202

Max Act: 0.3658. Min Act: -0.0000

Data Index: 369619 (The Pile)

Max Activating Token Index: 776

Text #14

Max Range: 0.6202. Min Range: -0.6202

Max Act: 0.3851. Min Act: -0.0000

Data Index: 1126149 (The Pile)

Max Activating Token Index: 637

Text #15

Max Range: 0.6202. Min Range: -0.6202

Max Act: 0.4028. Min Act: -0.0000

Data Index: 803224 (The Pile)

Max Activating Token Index: 839

Text #16

Max Range: 0.6202. Min Range: -0.6202

Max Act: 0.4186. Min Act: -0.0000

Data Index: 176551 (The Pile)

Max Activating Token Index: 652

Text #17

Max Range: 0.6202. Min Range: -0.6202

Max Act: 0.3700. Min Act: -0.0000

Data Index: 1012327 (The Pile)

Max Activating Token Index: 304

Text #18

Max Range: 0.6202. Min Range: -0.6202

Max Act: 0.3814. Min Act: -0.0000

Data Index: 293378 (The Pile)

Max Activating Token Index: 494

Text #19

Max Range: 0.6202. Min Range: -0.6202

Max Act: 0.3976. Min Act: -0.0000

Data Index: 546444 (The Pile)

Max Activating Token Index: 503