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

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

Neuron 1339 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2293. Min Range: -0.2293

Max Act: 0.2293. Min Act: -0.0003

Data Index: 1039915 (C4 (Web Text))

Max Activating Token Index: 948

Text #1

Max Range: 0.2293. Min Range: -0.2293

Max Act: 0.2154. Min Act: -0.0003

Data Index: 75772 (C4 (Web Text))

Max Activating Token Index: 711

Text #2

Max Range: 0.2293. Min Range: -0.2293

Max Act: 0.2288. Min Act: -0.0003

Data Index: 1203155 (C4 (Web Text))

Max Activating Token Index: 249

Text #3

Max Range: 0.2293. Min Range: -0.2293

Max Act: 0.2175. Min Act: -0.0003

Data Index: 919415 (C4 (Web Text))

Max Activating Token Index: 74

Text #4

Max Range: 0.2293. Min Range: -0.2293

Max Act: 0.2085. Min Act: -0.0003

Data Index: 1080085 (C4 (Web Text))

Max Activating Token Index: 910

Text #5

Max Range: 0.2293. Min Range: -0.2293

Max Act: 0.2014. Min Act: -0.0003

Data Index: 48804 (C4 (Web Text))

Max Activating Token Index: 302

Text #6

Max Range: 0.2293. Min Range: -0.2293

Max Act: 0.1986. Min Act: -0.0003

Data Index: 397003 (C4 (Web Text))

Max Activating Token Index: 87

Text #7

Max Range: 0.2293. Min Range: -0.2293

Max Act: 0.1915. Min Act: -0.0003

Data Index: 375857 (C4 (Web Text))

Max Activating Token Index: 111

Text #8

Max Range: 0.2293. Min Range: -0.2293

Max Act: 0.2034. Min Act: -0.0003

Data Index: 397324 (C4 (Web Text))

Max Activating Token Index: 81

Text #9

Max Range: 0.2293. Min Range: -0.2293

Max Act: 0.2017. Min Act: -0.0003

Data Index: 511095 (C4 (Web Text))

Max Activating Token Index: 867

Text #10

Max Range: 0.2293. Min Range: -0.2293

Max Act: 0.2024. Min Act: -0.0003

Data Index: 406140 (C4 (Web Text))

Max Activating Token Index: 306

Text #11

Max Range: 0.2293. Min Range: -0.2293

Max Act: 0.2013. Min Act: -0.0003

Data Index: 471944 (C4 (Web Text))

Max Activating Token Index: 516

Text #12

Max Range: 0.2293. Min Range: -0.2293

Max Act: 0.1937. Min Act: -0.0003

Data Index: 412037 (C4 (Web Text))

Max Activating Token Index: 854

Text #13

Max Range: 0.2293. Min Range: -0.2293

Max Act: 0.1922. Min Act: -0.0003

Data Index: 970617 (C4 (Web Text))

Max Activating Token Index: 450

Text #14

Max Range: 0.2293. Min Range: -0.2293

Max Act: 0.1926. Min Act: -0.0003

Data Index: 1241183 (C4 (Web Text))

Max Activating Token Index: 957

Text #15

Max Range: 0.2293. Min Range: -0.2293

Max Act: 0.1952. Min Act: -0.0003

Data Index: 295932 (C4 (Web Text))

Max Activating Token Index: 82

Text #16

Max Range: 0.2293. Min Range: -0.2293

Max Act: 0.1870. Min Act: -0.0003

Data Index: 1147098 (C4 (Web Text))

Max Activating Token Index: 225

Text #17

Max Range: 0.2293. Min Range: -0.2293

Max Act: 0.1861. Min Act: -0.0003

Data Index: 1083198 (C4 (Web Text))

Max Activating Token Index: 762

Text #18

Max Range: 0.2293. Min Range: -0.2293

Max Act: 0.1845. Min Act: -0.0003

Data Index: 927557 (C4 (Web Text))

Max Activating Token Index: 110

Text #19

Max Range: 0.2293. Min Range: -0.2293

Max Act: 0.1835. Min Act: -0.0003

Data Index: 525049 (C4 (Web Text))

Max Activating Token Index: 210