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

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

Neuron 2123 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7274. Min Range: -1.7274

Max Act: 1.7274. Min Act: -0.0000

Data Index: 196917 (C4 (Web Text))

Max Activating Token Index: 520

Text #1

Max Range: 1.7274. Min Range: -1.7274

Max Act: 1.5087. Min Act: -0.0000

Data Index: 953313 (C4 (Web Text))

Max Activating Token Index: 338

Text #2

Max Range: 1.7274. Min Range: -1.7274

Max Act: 1.4032. Min Act: -0.0000

Data Index: 67168 (C4 (Web Text))

Max Activating Token Index: 794

Text #3

Max Range: 1.7274. Min Range: -1.7274

Max Act: 1.3238. Min Act: -0.0000

Data Index: 1352712 (C4 (Web Text))

Max Activating Token Index: 199

Text #4

Max Range: 1.7274. Min Range: -1.7274

Max Act: 1.3230. Min Act: -0.0000

Data Index: 915634 (C4 (Web Text))

Max Activating Token Index: 643

Text #5

Max Range: 1.7274. Min Range: -1.7274

Max Act: 1.3819. Min Act: -0.0000

Data Index: 593223 (C4 (Web Text))

Max Activating Token Index: 284

Text #6

Max Range: 1.7274. Min Range: -1.7274

Max Act: 1.2111. Min Act: -0.0000

Data Index: 189480 (C4 (Web Text))

Max Activating Token Index: 142

Text #7

Max Range: 1.7274. Min Range: -1.7274

Max Act: 1.3563. Min Act: -0.0000

Data Index: 492509 (C4 (Web Text))

Max Activating Token Index: 21

Text #8

Max Range: 1.7274. Min Range: -1.7274

Max Act: 1.2759. Min Act: -0.0000

Data Index: 507650 (C4 (Web Text))

Max Activating Token Index: 620

Text #9

Max Range: 1.7274. Min Range: -1.7274

Max Act: 1.2564. Min Act: -0.0000

Data Index: 905256 (C4 (Web Text))

Max Activating Token Index: 569

Text #10

Max Range: 1.7274. Min Range: -1.7274

Max Act: 1.2115. Min Act: -0.0000

Data Index: 264792 (C4 (Web Text))

Max Activating Token Index: 254

Text #11

Max Range: 1.7274. Min Range: -1.7274

Max Act: 1.2101. Min Act: -0.0000

Data Index: 1079910 (C4 (Web Text))

Max Activating Token Index: 575

Text #12

Max Range: 1.7274. Min Range: -1.7274

Max Act: 1.2044. Min Act: -0.0000

Data Index: 944282 (C4 (Web Text))

Max Activating Token Index: 831

Text #13

Max Range: 1.7274. Min Range: -1.7274

Max Act: 1.1243. Min Act: -0.0000

Data Index: 858661 (C4 (Web Text))

Max Activating Token Index: 266

Text #14

Max Range: 1.7274. Min Range: -1.7274

Max Act: 1.1947. Min Act: -0.0000

Data Index: 844356 (C4 (Web Text))

Max Activating Token Index: 16

Text #15

Max Range: 1.7274. Min Range: -1.7274

Max Act: 1.1915. Min Act: -0.0000

Data Index: 778227 (C4 (Web Text))

Max Activating Token Index: 638

Text #16

Max Range: 1.7274. Min Range: -1.7274

Max Act: 1.1626. Min Act: -0.0000

Data Index: 187249 (C4 (Web Text))

Max Activating Token Index: 219

Text #17

Max Range: 1.7274. Min Range: -1.7274

Max Act: 1.1564. Min Act: -0.0000

Data Index: 596119 (C4 (Web Text))

Max Activating Token Index: 198

Text #18

Max Range: 1.7274. Min Range: -1.7274

Max Act: 1.2274. Min Act: -0.0000

Data Index: 425935 (C4 (Web Text))

Max Activating Token Index: 381

Text #19

Max Range: 1.7274. Min Range: -1.7274

Max Act: 1.1186. Min Act: -0.0000

Data Index: 179191 (C4 (Web Text))

Max Activating Token Index: 436