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

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

Neuron 2983 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2524. Min Range: -0.2524

Max Act: 0.2415. Min Act: -0.0002

Data Index: 239041 (C4 (Web Text))

Max Activating Token Index: 8

Text #1

Max Range: 0.2524. Min Range: -0.2524

Max Act: 0.2524. Min Act: -0.0001

Data Index: 1123802 (C4 (Web Text))

Max Activating Token Index: 119

Text #2

Max Range: 0.2524. Min Range: -0.2524

Max Act: 0.2350. Min Act: -0.0002

Data Index: 778427 (C4 (Web Text))

Max Activating Token Index: 910

Text #3

Max Range: 0.2524. Min Range: -0.2524

Max Act: 0.2363. Min Act: -0.0002

Data Index: 234132 (C4 (Web Text))

Max Activating Token Index: 262

Text #4

Max Range: 0.2524. Min Range: -0.2524

Max Act: 0.2257. Min Act: -0.0002

Data Index: 1016639 (C4 (Web Text))

Max Activating Token Index: 429

Text #5

Max Range: 0.2524. Min Range: -0.2524

Max Act: 0.2270. Min Act: -0.0002

Data Index: 101718 (C4 (Web Text))

Max Activating Token Index: 848

Text #6

Max Range: 0.2524. Min Range: -0.2524

Max Act: 0.2178. Min Act: -0.0002

Data Index: 673967 (C4 (Web Text))

Max Activating Token Index: 564

Text #7

Max Range: 0.2524. Min Range: -0.2524

Max Act: 0.2152. Min Act: -0.0001

Data Index: 625782 (C4 (Web Text))

Max Activating Token Index: 286

Text #8

Max Range: 0.2524. Min Range: -0.2524

Max Act: 0.2091. Min Act: -0.0002

Data Index: 665841 (C4 (Web Text))

Max Activating Token Index: 312

Text #9

Max Range: 0.2524. Min Range: -0.2524

Max Act: 0.2159. Min Act: -0.0002

Data Index: 686665 (C4 (Web Text))

Max Activating Token Index: 439

Text #10

Max Range: 0.2524. Min Range: -0.2524

Max Act: 0.2086. Min Act: -0.0002

Data Index: 202848 (C4 (Web Text))

Max Activating Token Index: 875

Text #11

Max Range: 0.2524. Min Range: -0.2524

Max Act: 0.2075. Min Act: -0.0002

Data Index: 1094833 (C4 (Web Text))

Max Activating Token Index: 194

Text #12

Max Range: 0.2524. Min Range: -0.2524

Max Act: 0.2037. Min Act: -0.0002

Data Index: 159901 (C4 (Web Text))

Max Activating Token Index: 262

Text #13

Max Range: 0.2524. Min Range: -0.2524

Max Act: 0.2008. Min Act: -0.0002

Data Index: 183804 (C4 (Web Text))

Max Activating Token Index: 490

Text #14

Max Range: 0.2524. Min Range: -0.2524

Max Act: 0.2014. Min Act: -0.0002

Data Index: 159058 (C4 (Web Text))

Max Activating Token Index: 915

Text #15

Max Range: 0.2524. Min Range: -0.2524

Max Act: 0.2006. Min Act: -0.0002

Data Index: 1092699 (C4 (Web Text))

Max Activating Token Index: 320

Text #16

Max Range: 0.2524. Min Range: -0.2524

Max Act: 0.2011. Min Act: -0.0002

Data Index: 919464 (C4 (Web Text))

Max Activating Token Index: 36

Text #17

Max Range: 0.2524. Min Range: -0.2524

Max Act: 0.1986. Min Act: -0.0002

Data Index: 812983 (C4 (Web Text))

Max Activating Token Index: 663

Text #18

Max Range: 0.2524. Min Range: -0.2524

Max Act: 0.1988. Min Act: -0.0002

Data Index: 1306474 (C4 (Web Text))

Max Activating Token Index: 357

Text #19

Max Range: 0.2524. Min Range: -0.2524

Max Act: 0.1957. Min Act: -0.0002

Data Index: 266152 (C4 (Web Text))

Max Activating Token Index: 26