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

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

Neuron 4146 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5265. Min Range: -2.5265

Max Act: 2.5265. Min Act: -0.0000

Data Index: 344511 (C4 (Web Text))

Max Activating Token Index: 94

Text #1

Max Range: 2.5265. Min Range: -2.5265

Max Act: 2.4092. Min Act: -0.0000

Data Index: 594240 (C4 (Web Text))

Max Activating Token Index: 930

Text #2

Max Range: 2.5265. Min Range: -2.5265

Max Act: 1.9414. Min Act: -0.0000

Data Index: 999704 (C4 (Web Text))

Max Activating Token Index: 87

Text #3

Max Range: 2.5265. Min Range: -2.5265

Max Act: 1.8483. Min Act: -0.0000

Data Index: 550854 (C4 (Web Text))

Max Activating Token Index: 868

Text #4

Max Range: 2.5265. Min Range: -2.5265

Max Act: 1.6330. Min Act: -0.0000

Data Index: 108116 (C4 (Web Text))

Max Activating Token Index: 549

Text #5

Max Range: 2.5265. Min Range: -2.5265

Max Act: 1.5150. Min Act: -0.0000

Data Index: 1351428 (C4 (Web Text))

Max Activating Token Index: 194

Text #6

Max Range: 2.5265. Min Range: -2.5265

Max Act: 1.3308. Min Act: -0.0000

Data Index: 171160 (C4 (Web Text))

Max Activating Token Index: 697

Text #7

Max Range: 2.5265. Min Range: -2.5265

Max Act: 1.4424. Min Act: -0.0001

Data Index: 959710 (C4 (Web Text))

Max Activating Token Index: 912

Text #8

Max Range: 2.5265. Min Range: -2.5265

Max Act: 1.4884. Min Act: -0.0001

Data Index: 43251 (C4 (Web Text))

Max Activating Token Index: 516

Text #9

Max Range: 2.5265. Min Range: -2.5265

Max Act: 1.3210. Min Act: -0.0000

Data Index: 131967 (C4 (Web Text))

Max Activating Token Index: 699

Text #10

Max Range: 2.5265. Min Range: -2.5265

Max Act: 1.3252. Min Act: -0.0000

Data Index: 567165 (C4 (Web Text))

Max Activating Token Index: 211

Text #11

Max Range: 2.5265. Min Range: -2.5265

Max Act: 1.3371. Min Act: -0.0000

Data Index: 455376 (C4 (Web Text))

Max Activating Token Index: 723

Text #12

Max Range: 2.5265. Min Range: -2.5265

Max Act: 1.3655. Min Act: -0.0000

Data Index: 465692 (C4 (Web Text))

Max Activating Token Index: 149

Text #13

Max Range: 2.5265. Min Range: -2.5265

Max Act: 1.3502. Min Act: -0.0000

Data Index: 488968 (C4 (Web Text))

Max Activating Token Index: 907

Text #14

Max Range: 2.5265. Min Range: -2.5265

Max Act: 1.3497. Min Act: -0.0000

Data Index: 512048 (C4 (Web Text))

Max Activating Token Index: 24

Text #15

Max Range: 2.5265. Min Range: -2.5265

Max Act: 1.2701. Min Act: -0.0000

Data Index: 85817 (C4 (Web Text))

Max Activating Token Index: 576

Text #16

Max Range: 2.5265. Min Range: -2.5265

Max Act: 1.2887. Min Act: -0.0000

Data Index: 393339 (C4 (Web Text))

Max Activating Token Index: 1006

Text #17

Max Range: 2.5265. Min Range: -2.5265

Max Act: 1.3023. Min Act: -0.0000

Data Index: 109944 (C4 (Web Text))

Max Activating Token Index: 626

Text #18

Max Range: 2.5265. Min Range: -2.5265

Max Act: 1.2235. Min Act: -0.0000

Data Index: 1056631 (C4 (Web Text))

Max Activating Token Index: 309

Text #19

Max Range: 2.5265. Min Range: -2.5265

Max Act: 1.0442. Min Act: -0.0000

Data Index: 285272 (C4 (Web Text))

Max Activating Token Index: 814