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

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

Neuron 1722 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: 1.0190. Min Range: -1.0190

Max Act: 1.0096. Min Act: -0.0000

Data Index: 1116731 (C4 (Web Text))

Max Activating Token Index: 257

Text #1

Max Range: 1.0190. Min Range: -1.0190

Max Act: 1.0190. Min Act: -0.0000

Data Index: 463306 (C4 (Web Text))

Max Activating Token Index: 738

Text #2

Max Range: 1.0190. Min Range: -1.0190

Max Act: 0.9144. Min Act: -0.0000

Data Index: 1333426 (C4 (Web Text))

Max Activating Token Index: 539

Text #3

Max Range: 1.0190. Min Range: -1.0190

Max Act: 0.9212. Min Act: -0.0000

Data Index: 209142 (C4 (Web Text))

Max Activating Token Index: 614

Text #4

Max Range: 1.0190. Min Range: -1.0190

Max Act: 0.8657. Min Act: -0.0001

Data Index: 999008 (C4 (Web Text))

Max Activating Token Index: 459

Text #5

Max Range: 1.0190. Min Range: -1.0190

Max Act: 0.8655. Min Act: -0.0000

Data Index: 774665 (C4 (Web Text))

Max Activating Token Index: 688

Text #6

Max Range: 1.0190. Min Range: -1.0190

Max Act: 0.8532. Min Act: -0.0000

Data Index: 137393 (C4 (Web Text))

Max Activating Token Index: 33

Text #7

Max Range: 1.0190. Min Range: -1.0190

Max Act: 0.8834. Min Act: -0.0001

Data Index: 1285168 (C4 (Web Text))

Max Activating Token Index: 200

Text #8

Max Range: 1.0190. Min Range: -1.0190

Max Act: 0.8453. Min Act: -0.0000

Data Index: 356368 (C4 (Web Text))

Max Activating Token Index: 432

Text #9

Max Range: 1.0190. Min Range: -1.0190

Max Act: 0.8639. Min Act: -0.0000

Data Index: 22942 (C4 (Web Text))

Max Activating Token Index: 492

Text #10

Max Range: 1.0190. Min Range: -1.0190

Max Act: 0.8106. Min Act: -0.0000

Data Index: 646694 (C4 (Web Text))

Max Activating Token Index: 651

Text #11

Max Range: 1.0190. Min Range: -1.0190

Max Act: 0.8406. Min Act: -0.0000

Data Index: 1178916 (C4 (Web Text))

Max Activating Token Index: 869

Text #12

Max Range: 1.0190. Min Range: -1.0190

Max Act: 0.8358. Min Act: -0.0001

Data Index: 532561 (C4 (Web Text))

Max Activating Token Index: 276

Text #13

Max Range: 1.0190. Min Range: -1.0190

Max Act: 0.8722. Min Act: -0.0000

Data Index: 662071 (C4 (Web Text))

Max Activating Token Index: 83

Text #14

Max Range: 1.0190. Min Range: -1.0190

Max Act: 0.8270. Min Act: -0.0001

Data Index: 315266 (C4 (Web Text))

Max Activating Token Index: 304

Text #15

Max Range: 1.0190. Min Range: -1.0190

Max Act: 0.8185. Min Act: -0.0000

Data Index: 733452 (C4 (Web Text))

Max Activating Token Index: 718

Text #16

Max Range: 1.0190. Min Range: -1.0190

Max Act: 0.8192. Min Act: -0.0000

Data Index: 769570 (C4 (Web Text))

Max Activating Token Index: 893

Text #17

Max Range: 1.0190. Min Range: -1.0190

Max Act: 0.8068. Min Act: -0.0000

Data Index: 164994 (C4 (Web Text))

Max Activating Token Index: 27

Text #18

Max Range: 1.0190. Min Range: -1.0190

Max Act: 0.8062. Min Act: -0.0000

Data Index: 493832 (C4 (Web Text))

Max Activating Token Index: 468

Text #19

Max Range: 1.0190. Min Range: -1.0190

Max Act: 0.8082. Min Act: -0.0000

Data Index: 842988 (C4 (Web Text))

Max Activating Token Index: 900