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

Dataset: The Pile

Neuron 3411 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7842. Min Range: -0.7842

Max Act: 0.7842. Min Act: -0.0000

Data Index: 541653 (The Pile)

Max Activating Token Index: 930

Text #1

Max Range: 0.7842. Min Range: -0.7842

Max Act: 0.6656. Min Act: -0.0000

Data Index: 166876 (The Pile)

Max Activating Token Index: 162

Text #2

Max Range: 0.7842. Min Range: -0.7842

Max Act: 0.6769. Min Act: -0.0000

Data Index: 720792 (The Pile)

Max Activating Token Index: 988

Text #3

Max Range: 0.7842. Min Range: -0.7842

Max Act: 0.7000. Min Act: -0.0000

Data Index: 1371243 (The Pile)

Max Activating Token Index: 354

Text #4

Max Range: 0.7842. Min Range: -0.7842

Max Act: 0.6273. Min Act: -0.0000

Data Index: 1137706 (The Pile)

Max Activating Token Index: 517

Text #5

Max Range: 0.7842. Min Range: -0.7842

Max Act: 0.6943. Min Act: -0.0000

Data Index: 1881807 (The Pile)

Max Activating Token Index: 998

Text #6

Max Range: 0.7842. Min Range: -0.7842

Max Act: 0.6358. Min Act: -0.0000

Data Index: 1400163 (The Pile)

Max Activating Token Index: 620

Text #7

Max Range: 0.7842. Min Range: -0.7842

Max Act: 0.6687. Min Act: -0.0000

Data Index: 805864 (The Pile)

Max Activating Token Index: 193

Text #8

Max Range: 0.7842. Min Range: -0.7842

Max Act: 0.6107. Min Act: -0.0000

Data Index: 414661 (The Pile)

Max Activating Token Index: 783

Text #9

Max Range: 0.7842. Min Range: -0.7842

Max Act: 0.5709. Min Act: -0.0000

Data Index: 239899 (The Pile)

Max Activating Token Index: 540

Text #10

Max Range: 0.7842. Min Range: -0.7842

Max Act: 0.6391. Min Act: -0.0000

Data Index: 890746 (The Pile)

Max Activating Token Index: 293

Text #11

Max Range: 0.7842. Min Range: -0.7842

Max Act: 0.6274. Min Act: -0.0000

Data Index: 1617474 (The Pile)

Max Activating Token Index: 570

Text #12

Max Range: 0.7842. Min Range: -0.7842

Max Act: 0.5782. Min Act: -0.0000

Data Index: 1452969 (The Pile)

Max Activating Token Index: 246

Text #13

Max Range: 0.7842. Min Range: -0.7842

Max Act: 0.6233. Min Act: -0.0000

Data Index: 1117397 (The Pile)

Max Activating Token Index: 264

Text #14

Max Range: 0.7842. Min Range: -0.7842

Max Act: 0.5716. Min Act: -0.0000

Data Index: 402706 (The Pile)

Max Activating Token Index: 745

Text #15

Max Range: 0.7842. Min Range: -0.7842

Max Act: 0.6044. Min Act: -0.0000

Data Index: 584912 (The Pile)

Max Activating Token Index: 44

Text #16

Max Range: 0.7842. Min Range: -0.7842

Max Act: 0.5309. Min Act: -0.0000

Data Index: 1757843 (The Pile)

Max Activating Token Index: 459

Text #17

Max Range: 0.7842. Min Range: -0.7842

Max Act: 0.5832. Min Act: -0.0000

Data Index: 966079 (The Pile)

Max Activating Token Index: 23

Text #18

Max Range: 0.7842. Min Range: -0.7842

Max Act: 0.5345. Min Act: -0.0000

Data Index: 80618 (The Pile)

Max Activating Token Index: 992

Text #19

Max Range: 0.7842. Min Range: -0.7842

Max Act: 0.5451. Min Act: -0.0000

Data Index: 1382053 (The Pile)

Max Activating Token Index: 808