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

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

Neuron 1633 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6059. Min Range: -0.6059

Max Act: 0.5847. Min Act: -0.0000

Data Index: 909472 (C4 (Web Text))

Max Activating Token Index: 247

Text #1

Max Range: 0.6059. Min Range: -0.6059

Max Act: 0.6059. Min Act: -0.0001

Data Index: 574928 (C4 (Web Text))

Max Activating Token Index: 333

Text #2

Max Range: 0.6059. Min Range: -0.6059

Max Act: 0.5758. Min Act: -0.0001

Data Index: 1227040 (C4 (Web Text))

Max Activating Token Index: 351

Text #3

Max Range: 0.6059. Min Range: -0.6059

Max Act: 0.5865. Min Act: -0.0001

Data Index: 728738 (C4 (Web Text))

Max Activating Token Index: 146

Text #4

Max Range: 0.6059. Min Range: -0.6059

Max Act: 0.5491. Min Act: -0.0001

Data Index: 156550 (C4 (Web Text))

Max Activating Token Index: 39

Text #5

Max Range: 0.6059. Min Range: -0.6059

Max Act: 0.5861. Min Act: -0.0000

Data Index: 413938 (C4 (Web Text))

Max Activating Token Index: 605

Text #6

Max Range: 0.6059. Min Range: -0.6059

Max Act: 0.5420. Min Act: -0.0000

Data Index: 336473 (C4 (Web Text))

Max Activating Token Index: 905

Text #7

Max Range: 0.6059. Min Range: -0.6059

Max Act: 0.5532. Min Act: -0.0001

Data Index: 375861 (C4 (Web Text))

Max Activating Token Index: 870

Text #8

Max Range: 0.6059. Min Range: -0.6059

Max Act: 0.5496. Min Act: -0.0000

Data Index: 711870 (C4 (Web Text))

Max Activating Token Index: 465

Text #9

Max Range: 0.6059. Min Range: -0.6059

Max Act: 0.5285. Min Act: -0.0001

Data Index: 1173990 (C4 (Web Text))

Max Activating Token Index: 824

Text #10

Max Range: 0.6059. Min Range: -0.6059

Max Act: 0.5216. Min Act: -0.0000

Data Index: 554087 (C4 (Web Text))

Max Activating Token Index: 1006

Text #11

Max Range: 0.6059. Min Range: -0.6059

Max Act: 0.5268. Min Act: -0.0001

Data Index: 1288535 (C4 (Web Text))

Max Activating Token Index: 1022

Text #12

Max Range: 0.6059. Min Range: -0.6059

Max Act: 0.5584. Min Act: -0.0001

Data Index: 889403 (C4 (Web Text))

Max Activating Token Index: 739

Text #13

Max Range: 0.6059. Min Range: -0.6059

Max Act: 0.4978. Min Act: -0.0000

Data Index: 862499 (C4 (Web Text))

Max Activating Token Index: 110

Text #14

Max Range: 0.6059. Min Range: -0.6059

Max Act: 0.5291. Min Act: -0.0001

Data Index: 804231 (C4 (Web Text))

Max Activating Token Index: 975

Text #15

Max Range: 0.6059. Min Range: -0.6059

Max Act: 0.5307. Min Act: -0.0000

Data Index: 13695 (C4 (Web Text))

Max Activating Token Index: 691

Text #16

Max Range: 0.6059. Min Range: -0.6059

Max Act: 0.5108. Min Act: -0.0000

Data Index: 1057397 (C4 (Web Text))

Max Activating Token Index: 957

Text #17

Max Range: 0.6059. Min Range: -0.6059

Max Act: 0.5159. Min Act: -0.0000

Data Index: 145396 (C4 (Web Text))

Max Activating Token Index: 653

Text #18

Max Range: 0.6059. Min Range: -0.6059

Max Act: 0.5033. Min Act: -0.0001

Data Index: 1266090 (C4 (Web Text))

Max Activating Token Index: 415

Text #19

Max Range: 0.6059. Min Range: -0.6059

Max Act: 0.5055. Min Act: -0.0001

Data Index: 253095 (C4 (Web Text))

Max Activating Token Index: 680