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

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

Neuron 752 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: 0.2461. Min Range: -0.2461

Max Act: 0.2461. Min Act: -0.0001

Data Index: 145626 (C4 (Web Text))

Max Activating Token Index: 96

Text #1

Max Range: 0.2461. Min Range: -0.2461

Max Act: 0.2176. Min Act: -0.0001

Data Index: 216280 (C4 (Web Text))

Max Activating Token Index: 820

Text #2

Max Range: 0.2461. Min Range: -0.2461

Max Act: 0.2235. Min Act: -0.0001

Data Index: 1023641 (C4 (Web Text))

Max Activating Token Index: 568

Text #3

Max Range: 0.2461. Min Range: -0.2461

Max Act: 0.2244. Min Act: -0.0001

Data Index: 1133609 (C4 (Web Text))

Max Activating Token Index: 339

Text #4

Max Range: 0.2461. Min Range: -0.2461

Max Act: 0.2222. Min Act: -0.0001

Data Index: 1055149 (C4 (Web Text))

Max Activating Token Index: 806

Text #5

Max Range: 0.2461. Min Range: -0.2461

Max Act: 0.2027. Min Act: -0.0001

Data Index: 43007 (C4 (Web Text))

Max Activating Token Index: 80

Text #6

Max Range: 0.2461. Min Range: -0.2461

Max Act: 0.2101. Min Act: -0.0001

Data Index: 1350536 (C4 (Web Text))

Max Activating Token Index: 92

Text #7

Max Range: 0.2461. Min Range: -0.2461

Max Act: 0.2003. Min Act: -0.0001

Data Index: 270649 (C4 (Web Text))

Max Activating Token Index: 334

Text #8

Max Range: 0.2461. Min Range: -0.2461

Max Act: 0.2054. Min Act: -0.0001

Data Index: 699690 (C4 (Web Text))

Max Activating Token Index: 425

Text #9

Max Range: 0.2461. Min Range: -0.2461

Max Act: 0.2117. Min Act: -0.0001

Data Index: 832006 (C4 (Web Text))

Max Activating Token Index: 780

Text #10

Max Range: 0.2461. Min Range: -0.2461

Max Act: 0.2019. Min Act: -0.0001

Data Index: 825164 (C4 (Web Text))

Max Activating Token Index: 203

Text #11

Max Range: 0.2461. Min Range: -0.2461

Max Act: 0.2015. Min Act: -0.0001

Data Index: 609785 (C4 (Web Text))

Max Activating Token Index: 461

Text #12

Max Range: 0.2461. Min Range: -0.2461

Max Act: 0.2004. Min Act: -0.0001

Data Index: 433264 (C4 (Web Text))

Max Activating Token Index: 994

Text #13

Max Range: 0.2461. Min Range: -0.2461

Max Act: 0.1930. Min Act: -0.0001

Data Index: 83684 (C4 (Web Text))

Max Activating Token Index: 258

Text #14

Max Range: 0.2461. Min Range: -0.2461

Max Act: 0.1982. Min Act: -0.0001

Data Index: 1186465 (C4 (Web Text))

Max Activating Token Index: 126

Text #15

Max Range: 0.2461. Min Range: -0.2461

Max Act: 0.1973. Min Act: -0.0001

Data Index: 598409 (C4 (Web Text))

Max Activating Token Index: 224

Text #16

Max Range: 0.2461. Min Range: -0.2461

Max Act: 0.1898. Min Act: -0.0001

Data Index: 92122 (C4 (Web Text))

Max Activating Token Index: 618

Text #17

Max Range: 0.2461. Min Range: -0.2461

Max Act: 0.1884. Min Act: -0.0001

Data Index: 78033 (C4 (Web Text))

Max Activating Token Index: 870

Text #18

Max Range: 0.2461. Min Range: -0.2461

Max Act: 0.1996. Min Act: -0.0001

Data Index: 817472 (C4 (Web Text))

Max Activating Token Index: 269

Text #19

Max Range: 0.2461. Min Range: -0.2461

Max Act: 0.1846. Min Act: -0.0001

Data Index: 962141 (C4 (Web Text))

Max Activating Token Index: 352