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

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

Neuron 5552 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: 1.2242. Min Range: -1.2242

Max Act: 1.2235. Min Act: -0.0000

Data Index: 689301 (C4 (Web Text))

Max Activating Token Index: 777

Text #1

Max Range: 1.2242. Min Range: -1.2242

Max Act: 1.1095. Min Act: -0.0000

Data Index: 612267 (C4 (Web Text))

Max Activating Token Index: 201

Text #2

Max Range: 1.2242. Min Range: -1.2242

Max Act: 1.2242. Min Act: -0.0000

Data Index: 421191 (C4 (Web Text))

Max Activating Token Index: 541

Text #3

Max Range: 1.2242. Min Range: -1.2242

Max Act: 1.1985. Min Act: -0.0000

Data Index: 299437 (C4 (Web Text))

Max Activating Token Index: 190

Text #4

Max Range: 1.2242. Min Range: -1.2242

Max Act: 1.0307. Min Act: -0.0000

Data Index: 76904 (C4 (Web Text))

Max Activating Token Index: 109

Text #5

Max Range: 1.2242. Min Range: -1.2242

Max Act: 1.1419. Min Act: -0.0000

Data Index: 1256664 (C4 (Web Text))

Max Activating Token Index: 100

Text #6

Max Range: 1.2242. Min Range: -1.2242

Max Act: 1.2011. Min Act: -0.0000

Data Index: 216014 (C4 (Web Text))

Max Activating Token Index: 372

Text #7

Max Range: 1.2242. Min Range: -1.2242

Max Act: 1.1939. Min Act: -0.0000

Data Index: 1061248 (C4 (Web Text))

Max Activating Token Index: 670

Text #8

Max Range: 1.2242. Min Range: -1.2242

Max Act: 1.0091. Min Act: -0.0000

Data Index: 522135 (C4 (Web Text))

Max Activating Token Index: 831

Text #9

Max Range: 1.2242. Min Range: -1.2242

Max Act: 0.9566. Min Act: -0.0000

Data Index: 1224327 (C4 (Web Text))

Max Activating Token Index: 364

Text #10

Max Range: 1.2242. Min Range: -1.2242

Max Act: 0.9254. Min Act: -0.0000

Data Index: 378659 (C4 (Web Text))

Max Activating Token Index: 247

Text #11

Max Range: 1.2242. Min Range: -1.2242

Max Act: 0.9347. Min Act: -0.0000

Data Index: 1179293 (C4 (Web Text))

Max Activating Token Index: 858

Text #12

Max Range: 1.2242. Min Range: -1.2242

Max Act: 0.9163. Min Act: -0.0000

Data Index: 745486 (C4 (Web Text))

Max Activating Token Index: 547

Text #13

Max Range: 1.2242. Min Range: -1.2242

Max Act: 0.9699. Min Act: -0.0000

Data Index: 189047 (C4 (Web Text))

Max Activating Token Index: 955

Text #14

Max Range: 1.2242. Min Range: -1.2242

Max Act: 0.8788. Min Act: -0.0000

Data Index: 1176779 (C4 (Web Text))

Max Activating Token Index: 785

Text #15

Max Range: 1.2242. Min Range: -1.2242

Max Act: 0.8791. Min Act: -0.0000

Data Index: 1336840 (C4 (Web Text))

Max Activating Token Index: 829

Text #16

Max Range: 1.2242. Min Range: -1.2242

Max Act: 0.8150. Min Act: -0.0000

Data Index: 210328 (C4 (Web Text))

Max Activating Token Index: 271

Text #17

Max Range: 1.2242. Min Range: -1.2242

Max Act: 0.9074. Min Act: -0.0000

Data Index: 476327 (C4 (Web Text))

Max Activating Token Index: 881

Text #18

Max Range: 1.2242. Min Range: -1.2242

Max Act: 0.8230. Min Act: -0.0000

Data Index: 821418 (C4 (Web Text))

Max Activating Token Index: 22

Text #19

Max Range: 1.2242. Min Range: -1.2242

Max Act: 0.8062. Min Act: -0.0000

Data Index: 65914 (C4 (Web Text))

Max Activating Token Index: 597