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

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

Neuron 333 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2289. Min Range: -0.2289

Max Act: 0.2289. Min Act: -0.0001

Data Index: 967745 (C4 (Web Text))

Max Activating Token Index: 451

Text #1

Max Range: 0.2289. Min Range: -0.2289

Max Act: 0.2226. Min Act: -0.0000

Data Index: 1020129 (C4 (Web Text))

Max Activating Token Index: 70

Text #2

Max Range: 0.2289. Min Range: -0.2289

Max Act: 0.2271. Min Act: -0.0001

Data Index: 307379 (C4 (Web Text))

Max Activating Token Index: 288

Text #3

Max Range: 0.2289. Min Range: -0.2289

Max Act: 0.2246. Min Act: -0.0000

Data Index: 225390 (C4 (Web Text))

Max Activating Token Index: 557

Text #4

Max Range: 0.2289. Min Range: -0.2289

Max Act: 0.2067. Min Act: -0.0001

Data Index: 291446 (C4 (Web Text))

Max Activating Token Index: 944

Text #5

Max Range: 0.2289. Min Range: -0.2289

Max Act: 0.2069. Min Act: -0.0000

Data Index: 589114 (C4 (Web Text))

Max Activating Token Index: 953

Text #6

Max Range: 0.2289. Min Range: -0.2289

Max Act: 0.1974. Min Act: -0.0001

Data Index: 378277 (C4 (Web Text))

Max Activating Token Index: 873

Text #7

Max Range: 0.2289. Min Range: -0.2289

Max Act: 0.1914. Min Act: -0.0001

Data Index: 1055522 (C4 (Web Text))

Max Activating Token Index: 804

Text #8

Max Range: 0.2289. Min Range: -0.2289

Max Act: 0.1842. Min Act: -0.0001

Data Index: 1335488 (C4 (Web Text))

Max Activating Token Index: 619

Text #9

Max Range: 0.2289. Min Range: -0.2289

Max Act: 0.1877. Min Act: -0.0000

Data Index: 825914 (C4 (Web Text))

Max Activating Token Index: 167

Text #10

Max Range: 0.2289. Min Range: -0.2289

Max Act: 0.1955. Min Act: -0.0001

Data Index: 904284 (C4 (Web Text))

Max Activating Token Index: 648

Text #11

Max Range: 0.2289. Min Range: -0.2289

Max Act: 0.1853. Min Act: -0.0001

Data Index: 587480 (C4 (Web Text))

Max Activating Token Index: 614

Text #12

Max Range: 0.2289. Min Range: -0.2289

Max Act: 0.1865. Min Act: -0.0001

Data Index: 505345 (C4 (Web Text))

Max Activating Token Index: 233

Text #13

Max Range: 0.2289. Min Range: -0.2289

Max Act: 0.1827. Min Act: -0.0001

Data Index: 1129202 (C4 (Web Text))

Max Activating Token Index: 524

Text #14

Max Range: 0.2289. Min Range: -0.2289

Max Act: 0.1826. Min Act: -0.0001

Data Index: 730126 (C4 (Web Text))

Max Activating Token Index: 659

Text #15

Max Range: 0.2289. Min Range: -0.2289

Max Act: 0.1883. Min Act: -0.0000

Data Index: 544875 (C4 (Web Text))

Max Activating Token Index: 185

Text #16

Max Range: 0.2289. Min Range: -0.2289

Max Act: 0.1882. Min Act: -0.0001

Data Index: 324904 (C4 (Web Text))

Max Activating Token Index: 386

Text #17

Max Range: 0.2289. Min Range: -0.2289

Max Act: 0.1797. Min Act: -0.0001

Data Index: 491843 (C4 (Web Text))

Max Activating Token Index: 205

Text #18

Max Range: 0.2289. Min Range: -0.2289

Max Act: 0.1833. Min Act: -0.0001

Data Index: 1279836 (C4 (Web Text))

Max Activating Token Index: 90

Text #19

Max Range: 0.2289. Min Range: -0.2289

Max Act: 0.1765. Min Act: -0.0000

Data Index: 1006406 (C4 (Web Text))

Max Activating Token Index: 492