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

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

Neuron 3842 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3382. Min Range: -0.3382

Max Act: 0.3382. Min Act: -0.0001

Data Index: 767885 (C4 (Web Text))

Max Activating Token Index: 162

Text #1

Max Range: 0.3382. Min Range: -0.3382

Max Act: 0.2561. Min Act: -0.0001

Data Index: 129890 (C4 (Web Text))

Max Activating Token Index: 983

Text #2

Max Range: 0.3382. Min Range: -0.3382

Max Act: 0.2316. Min Act: -0.0001

Data Index: 999575 (C4 (Web Text))

Max Activating Token Index: 835

Text #3

Max Range: 0.3382. Min Range: -0.3382

Max Act: 0.2361. Min Act: -0.0001

Data Index: 1065439 (C4 (Web Text))

Max Activating Token Index: 382

Text #4

Max Range: 0.3382. Min Range: -0.3382

Max Act: 0.2093. Min Act: -0.0001

Data Index: 388194 (C4 (Web Text))

Max Activating Token Index: 659

Text #5

Max Range: 0.3382. Min Range: -0.3382

Max Act: 0.2320. Min Act: -0.0001

Data Index: 225921 (C4 (Web Text))

Max Activating Token Index: 612

Text #6

Max Range: 0.3382. Min Range: -0.3382

Max Act: 0.2140. Min Act: -0.0001

Data Index: 328580 (C4 (Web Text))

Max Activating Token Index: 533

Text #7

Max Range: 0.3382. Min Range: -0.3382

Max Act: 0.2037. Min Act: -0.0001

Data Index: 936416 (C4 (Web Text))

Max Activating Token Index: 199

Text #8

Max Range: 0.3382. Min Range: -0.3382

Max Act: 0.2095. Min Act: -0.0001

Data Index: 156651 (C4 (Web Text))

Max Activating Token Index: 453

Text #9

Max Range: 0.3382. Min Range: -0.3382

Max Act: 0.1997. Min Act: -0.0001

Data Index: 537141 (C4 (Web Text))

Max Activating Token Index: 691

Text #10

Max Range: 0.3382. Min Range: -0.3382

Max Act: 0.2056. Min Act: -0.0001

Data Index: 277843 (C4 (Web Text))

Max Activating Token Index: 838

Text #11

Max Range: 0.3382. Min Range: -0.3382

Max Act: 0.2095. Min Act: -0.0001

Data Index: 1219150 (C4 (Web Text))

Max Activating Token Index: 964

Text #12

Max Range: 0.3382. Min Range: -0.3382

Max Act: 0.2015. Min Act: -0.0001

Data Index: 1316863 (C4 (Web Text))

Max Activating Token Index: 391

Text #13

Max Range: 0.3382. Min Range: -0.3382

Max Act: 0.2012. Min Act: -0.0001

Data Index: 280182 (C4 (Web Text))

Max Activating Token Index: 727

Text #14

Max Range: 0.3382. Min Range: -0.3382

Max Act: 0.1915. Min Act: -0.0001

Data Index: 912655 (C4 (Web Text))

Max Activating Token Index: 919

Text #15

Max Range: 0.3382. Min Range: -0.3382

Max Act: 0.1892. Min Act: -0.0001

Data Index: 1094955 (C4 (Web Text))

Max Activating Token Index: 1016

Text #16

Max Range: 0.3382. Min Range: -0.3382

Max Act: 0.2002. Min Act: -0.0001

Data Index: 961500 (C4 (Web Text))

Max Activating Token Index: 106

Text #17

Max Range: 0.3382. Min Range: -0.3382

Max Act: 0.1730. Min Act: -0.0001

Data Index: 428784 (C4 (Web Text))

Max Activating Token Index: 640

Text #18

Max Range: 0.3382. Min Range: -0.3382

Max Act: 0.1816. Min Act: -0.0001

Data Index: 78332 (C4 (Web Text))

Max Activating Token Index: 221

Text #19

Max Range: 0.3382. Min Range: -0.3382

Max Act: 0.1945. Min Act: -0.0001

Data Index: 891997 (C4 (Web Text))

Max Activating Token Index: 660