Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1604 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.0232. Min Range: -1.0232

Max Act: 1.0232. Min Act: -0.0000

Data Index: 1148823 (C4 (Web Text))

Max Activating Token Index: 323

Text #1

Max Range: 1.0232. Min Range: -1.0232

Max Act: 0.7498. Min Act: -0.0000

Data Index: 154166 (C4 (Web Text))

Max Activating Token Index: 338

Text #2

Max Range: 1.0232. Min Range: -1.0232

Max Act: 0.6754. Min Act: -0.0000

Data Index: 657792 (C4 (Web Text))

Max Activating Token Index: 814

Text #3

Max Range: 1.0232. Min Range: -1.0232

Max Act: 0.6527. Min Act: -0.0000

Data Index: 682817 (C4 (Web Text))

Max Activating Token Index: 792

Text #4

Max Range: 1.0232. Min Range: -1.0232

Max Act: 0.6233. Min Act: -0.0000

Data Index: 899910 (C4 (Web Text))

Max Activating Token Index: 767

Text #5

Max Range: 1.0232. Min Range: -1.0232

Max Act: 0.5085. Min Act: -0.0000

Data Index: 432282 (C4 (Web Text))

Max Activating Token Index: 706

Text #6

Max Range: 1.0232. Min Range: -1.0232

Max Act: 0.5016. Min Act: -0.0000

Data Index: 399928 (C4 (Web Text))

Max Activating Token Index: 848

Text #7

Max Range: 1.0232. Min Range: -1.0232

Max Act: 0.5226. Min Act: -0.0000

Data Index: 280221 (C4 (Web Text))

Max Activating Token Index: 69

Text #8

Max Range: 1.0232. Min Range: -1.0232

Max Act: 0.5034. Min Act: -0.0000

Data Index: 925004 (C4 (Web Text))

Max Activating Token Index: 101

Text #9

Max Range: 1.0232. Min Range: -1.0232

Max Act: 0.4556. Min Act: -0.0000

Data Index: 1134133 (C4 (Web Text))

Max Activating Token Index: 331

Text #10

Max Range: 1.0232. Min Range: -1.0232

Max Act: 0.4701. Min Act: -0.0000

Data Index: 461595 (C4 (Web Text))

Max Activating Token Index: 773

Text #11

Max Range: 1.0232. Min Range: -1.0232

Max Act: 0.4386. Min Act: 0.0000

Data Index: 860153 (C4 (Web Text))

Max Activating Token Index: 972

Text #12

Max Range: 1.0232. Min Range: -1.0232

Max Act: 0.4044. Min Act: 0.0000

Data Index: 1258747 (C4 (Web Text))

Max Activating Token Index: 174

Text #13

Max Range: 1.0232. Min Range: -1.0232

Max Act: 0.4084. Min Act: -0.0000

Data Index: 961260 (C4 (Web Text))

Max Activating Token Index: 923

Text #14

Max Range: 1.0232. Min Range: -1.0232

Max Act: 0.4123. Min Act: -0.0000

Data Index: 239766 (C4 (Web Text))

Max Activating Token Index: 589

Text #15

Max Range: 1.0232. Min Range: -1.0232

Max Act: 0.4007. Min Act: -0.0000

Data Index: 277653 (C4 (Web Text))

Max Activating Token Index: 92

Text #16

Max Range: 1.0232. Min Range: -1.0232

Max Act: 0.3960. Min Act: -0.0000

Data Index: 261679 (C4 (Web Text))

Max Activating Token Index: 546

Text #17

Max Range: 1.0232. Min Range: -1.0232

Max Act: 0.3531. Min Act: -0.0000

Data Index: 817216 (C4 (Web Text))

Max Activating Token Index: 913

Text #18

Max Range: 1.0232. Min Range: -1.0232

Max Act: 0.3785. Min Act: -0.0000

Data Index: 897933 (C4 (Web Text))

Max Activating Token Index: 1007

Text #19

Max Range: 1.0232. Min Range: -1.0232

Max Act: 0.3663. Min Act: -0.0000

Data Index: 491452 (C4 (Web Text))

Max Activating Token Index: 428