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

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

Neuron 6005 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8271. Min Range: -2.8271

Max Act: 2.8271. Min Act: -0.0000

Data Index: 855291 (C4 (Web Text))

Max Activating Token Index: 1000

Text #1

Max Range: 2.8271. Min Range: -2.8271

Max Act: 2.3320. Min Act: -0.0000

Data Index: 976359 (C4 (Web Text))

Max Activating Token Index: 375

Text #2

Max Range: 2.8271. Min Range: -2.8271

Max Act: 2.2824. Min Act: -0.0000

Data Index: 107083 (C4 (Web Text))

Max Activating Token Index: 1000

Text #3

Max Range: 2.8271. Min Range: -2.8271

Max Act: 2.3907. Min Act: -0.0000

Data Index: 489913 (C4 (Web Text))

Max Activating Token Index: 931

Text #4

Max Range: 2.8271. Min Range: -2.8271

Max Act: 2.2831. Min Act: -0.0000

Data Index: 630476 (C4 (Web Text))

Max Activating Token Index: 957

Text #5

Max Range: 2.8271. Min Range: -2.8271

Max Act: 2.2664. Min Act: -0.0000

Data Index: 390765 (C4 (Web Text))

Max Activating Token Index: 1011

Text #6

Max Range: 2.8271. Min Range: -2.8271

Max Act: 2.2086. Min Act: -0.0000

Data Index: 1128586 (C4 (Web Text))

Max Activating Token Index: 89

Text #7

Max Range: 2.8271. Min Range: -2.8271

Max Act: 1.9635. Min Act: -0.0000

Data Index: 1042254 (C4 (Web Text))

Max Activating Token Index: 795

Text #8

Max Range: 2.8271. Min Range: -2.8271

Max Act: 2.0716. Min Act: -0.0000

Data Index: 1087521 (C4 (Web Text))

Max Activating Token Index: 177

Text #9

Max Range: 2.8271. Min Range: -2.8271

Max Act: 2.1118. Min Act: -0.0000

Data Index: 574608 (C4 (Web Text))

Max Activating Token Index: 244

Text #10

Max Range: 2.8271. Min Range: -2.8271

Max Act: 1.9847. Min Act: -0.0000

Data Index: 710514 (C4 (Web Text))

Max Activating Token Index: 983

Text #11

Max Range: 2.8271. Min Range: -2.8271

Max Act: 2.0505. Min Act: -0.0000

Data Index: 1063277 (C4 (Web Text))

Max Activating Token Index: 716

Text #12

Max Range: 2.8271. Min Range: -2.8271

Max Act: 2.0181. Min Act: -0.0000

Data Index: 140117 (C4 (Web Text))

Max Activating Token Index: 570

Text #13

Max Range: 2.8271. Min Range: -2.8271

Max Act: 1.7818. Min Act: -0.0000

Data Index: 367451 (C4 (Web Text))

Max Activating Token Index: 151

Text #14

Max Range: 2.8271. Min Range: -2.8271

Max Act: 1.8663. Min Act: -0.0000

Data Index: 1269462 (C4 (Web Text))

Max Activating Token Index: 68

Text #15

Max Range: 2.8271. Min Range: -2.8271

Max Act: 2.0080. Min Act: -0.0000

Data Index: 644041 (C4 (Web Text))

Max Activating Token Index: 761

Text #16

Max Range: 2.8271. Min Range: -2.8271

Max Act: 1.8142. Min Act: -0.0000

Data Index: 313458 (C4 (Web Text))

Max Activating Token Index: 120

Text #17

Max Range: 2.8271. Min Range: -2.8271

Max Act: 1.8127. Min Act: -0.0000

Data Index: 1244093 (C4 (Web Text))

Max Activating Token Index: 186

Text #18

Max Range: 2.8271. Min Range: -2.8271

Max Act: 1.7180. Min Act: -0.0000

Data Index: 198678 (C4 (Web Text))

Max Activating Token Index: 115

Text #19

Max Range: 2.8271. Min Range: -2.8271

Max Act: 1.6242. Min Act: -0.0000

Data Index: 12996 (C4 (Web Text))

Max Activating Token Index: 134