Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 839 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2235. Min Range: -0.2235

Max Act: 0.2235. Min Act: -0.0001

Data Index: 946928 (C4 (Web Text))

Max Activating Token Index: 856

Text #1

Max Range: 0.2235. Min Range: -0.2235

Max Act: 0.2189. Min Act: -0.0001

Data Index: 611010 (C4 (Web Text))

Max Activating Token Index: 62

Text #2

Max Range: 0.2235. Min Range: -0.2235

Max Act: 0.2046. Min Act: -0.0001

Data Index: 454446 (C4 (Web Text))

Max Activating Token Index: 292

Text #3

Max Range: 0.2235. Min Range: -0.2235

Max Act: 0.2111. Min Act: -0.0001

Data Index: 1196504 (C4 (Web Text))

Max Activating Token Index: 294

Text #4

Max Range: 0.2235. Min Range: -0.2235

Max Act: 0.2163. Min Act: -0.0001

Data Index: 21392 (C4 (Web Text))

Max Activating Token Index: 388

Text #5

Max Range: 0.2235. Min Range: -0.2235

Max Act: 0.2108. Min Act: -0.0001

Data Index: 143556 (C4 (Web Text))

Max Activating Token Index: 803

Text #6

Max Range: 0.2235. Min Range: -0.2235

Max Act: 0.2010. Min Act: -0.0001

Data Index: 1339500 (C4 (Web Text))

Max Activating Token Index: 679

Text #7

Max Range: 0.2235. Min Range: -0.2235

Max Act: 0.2227. Min Act: -0.0001

Data Index: 31829 (C4 (Web Text))

Max Activating Token Index: 784

Text #8

Max Range: 0.2235. Min Range: -0.2235

Max Act: 0.2111. Min Act: -0.0001

Data Index: 853493 (C4 (Web Text))

Max Activating Token Index: 384

Text #9

Max Range: 0.2235. Min Range: -0.2235

Max Act: 0.2052. Min Act: -0.0001

Data Index: 801255 (C4 (Web Text))

Max Activating Token Index: 390

Text #10

Max Range: 0.2235. Min Range: -0.2235

Max Act: 0.1979. Min Act: -0.0001

Data Index: 511542 (C4 (Web Text))

Max Activating Token Index: 707

Text #11

Max Range: 0.2235. Min Range: -0.2235

Max Act: 0.1941. Min Act: -0.0001

Data Index: 1124304 (C4 (Web Text))

Max Activating Token Index: 416

Text #12

Max Range: 0.2235. Min Range: -0.2235

Max Act: 0.1996. Min Act: -0.0001

Data Index: 805715 (C4 (Web Text))

Max Activating Token Index: 454

Text #13

Max Range: 0.2235. Min Range: -0.2235

Max Act: 0.1984. Min Act: -0.0001

Data Index: 126222 (C4 (Web Text))

Max Activating Token Index: 21

Text #14

Max Range: 0.2235. Min Range: -0.2235

Max Act: 0.1999. Min Act: -0.0001

Data Index: 1264911 (C4 (Web Text))

Max Activating Token Index: 817

Text #15

Max Range: 0.2235. Min Range: -0.2235

Max Act: 0.1914. Min Act: -0.0001

Data Index: 938701 (C4 (Web Text))

Max Activating Token Index: 517

Text #16

Max Range: 0.2235. Min Range: -0.2235

Max Act: 0.1776. Min Act: -0.0001

Data Index: 277236 (C4 (Web Text))

Max Activating Token Index: 665

Text #17

Max Range: 0.2235. Min Range: -0.2235

Max Act: 0.1882. Min Act: -0.0001

Data Index: 388905 (C4 (Web Text))

Max Activating Token Index: 927

Text #18

Max Range: 0.2235. Min Range: -0.2235

Max Act: 0.1940. Min Act: -0.0001

Data Index: 911100 (C4 (Web Text))

Max Activating Token Index: 382

Text #19

Max Range: 0.2235. Min Range: -0.2235

Max Act: 0.1990. Min Act: -0.0001

Data Index: 158294 (C4 (Web Text))

Max Activating Token Index: 753