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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1871 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8955. Min Range: -1.8955

Max Act: 1.6253. Min Act: -0.0000

Data Index: 1305319 (C4 (Web Text))

Max Activating Token Index: 824

Text #1

Max Range: 1.8955. Min Range: -1.8955

Max Act: 1.6939. Min Act: -0.0000

Data Index: 207619 (C4 (Web Text))

Max Activating Token Index: 314

Text #2

Max Range: 1.8955. Min Range: -1.8955

Max Act: 1.7841. Min Act: -0.0000

Data Index: 240019 (C4 (Web Text))

Max Activating Token Index: 231

Text #3

Max Range: 1.8955. Min Range: -1.8955

Max Act: 1.7815. Min Act: -0.0000

Data Index: 503263 (C4 (Web Text))

Max Activating Token Index: 179

Text #4

Max Range: 1.8955. Min Range: -1.8955

Max Act: 1.5585. Min Act: -0.0000

Data Index: 1302560 (C4 (Web Text))

Max Activating Token Index: 460

Text #5

Max Range: 1.8955. Min Range: -1.8955

Max Act: 1.4406. Min Act: -0.0000

Data Index: 639689 (C4 (Web Text))

Max Activating Token Index: 637

Text #6

Max Range: 1.8955. Min Range: -1.8955

Max Act: 1.7122. Min Act: -0.0000

Data Index: 846766 (C4 (Web Text))

Max Activating Token Index: 315

Text #7

Max Range: 1.8955. Min Range: -1.8955

Max Act: 1.7778. Min Act: -0.0000

Data Index: 761 (C4 (Web Text))

Max Activating Token Index: 121

Text #8

Max Range: 1.8955. Min Range: -1.8955

Max Act: 1.8955. Min Act: -0.0000

Data Index: 980437 (C4 (Web Text))

Max Activating Token Index: 805

Text #9

Max Range: 1.8955. Min Range: -1.8955

Max Act: 1.6508. Min Act: -0.0000

Data Index: 734004 (C4 (Web Text))

Max Activating Token Index: 724

Text #10

Max Range: 1.8955. Min Range: -1.8955

Max Act: 1.5480. Min Act: -0.0000

Data Index: 268610 (C4 (Web Text))

Max Activating Token Index: 765

Text #11

Max Range: 1.8955. Min Range: -1.8955

Max Act: 1.4706. Min Act: -0.0000

Data Index: 1259021 (C4 (Web Text))

Max Activating Token Index: 783

Text #12

Max Range: 1.8955. Min Range: -1.8955

Max Act: 1.6428. Min Act: -0.0000

Data Index: 819733 (C4 (Web Text))

Max Activating Token Index: 81

Text #13

Max Range: 1.8955. Min Range: -1.8955

Max Act: 1.6226. Min Act: -0.0000

Data Index: 137747 (C4 (Web Text))

Max Activating Token Index: 928

Text #14

Max Range: 1.8955. Min Range: -1.8955

Max Act: 1.6073. Min Act: -0.0000

Data Index: 415554 (C4 (Web Text))

Max Activating Token Index: 578

Text #15

Max Range: 1.8955. Min Range: -1.8955

Max Act: 1.6145. Min Act: -0.0000

Data Index: 163054 (C4 (Web Text))

Max Activating Token Index: 36

Text #16

Max Range: 1.8955. Min Range: -1.8955

Max Act: 1.4295. Min Act: -0.0000

Data Index: 971345 (C4 (Web Text))

Max Activating Token Index: 111

Text #17

Max Range: 1.8955. Min Range: -1.8955

Max Act: 1.4142. Min Act: -0.0000

Data Index: 1337406 (C4 (Web Text))

Max Activating Token Index: 440

Text #18

Max Range: 1.8955. Min Range: -1.8955

Max Act: 1.4213. Min Act: -0.0000

Data Index: 150332 (C4 (Web Text))

Max Activating Token Index: 936

Text #19

Max Range: 1.8955. Min Range: -1.8955

Max Act: 1.4941. Min Act: -0.0000

Data Index: 1316178 (C4 (Web Text))

Max Activating Token Index: 471