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

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

Neuron 2644 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: 0.8500. Min Range: -0.8500

Max Act: 0.7900. Min Act: -0.0003

Data Index: 683241 (C4 (Web Text))

Max Activating Token Index: 584

Text #1

Max Range: 0.8500. Min Range: -0.8500

Max Act: 0.8500. Min Act: -0.0003

Data Index: 490387 (C4 (Web Text))

Max Activating Token Index: 90

Text #2

Max Range: 0.8500. Min Range: -0.8500

Max Act: 0.7324. Min Act: -0.0003

Data Index: 1253308 (C4 (Web Text))

Max Activating Token Index: 309

Text #3

Max Range: 0.8500. Min Range: -0.8500

Max Act: 0.7041. Min Act: -0.0003

Data Index: 1278506 (C4 (Web Text))

Max Activating Token Index: 190

Text #4

Max Range: 0.8500. Min Range: -0.8500

Max Act: 0.7199. Min Act: -0.0003

Data Index: 233462 (C4 (Web Text))

Max Activating Token Index: 126

Text #5

Max Range: 0.8500. Min Range: -0.8500

Max Act: 0.7110. Min Act: -0.0003

Data Index: 1102673 (C4 (Web Text))

Max Activating Token Index: 84

Text #6

Max Range: 0.8500. Min Range: -0.8500

Max Act: 0.6894. Min Act: -0.0003

Data Index: 699222 (C4 (Web Text))

Max Activating Token Index: 92

Text #7

Max Range: 0.8500. Min Range: -0.8500

Max Act: 0.6868. Min Act: -0.0003

Data Index: 598169 (C4 (Web Text))

Max Activating Token Index: 141

Text #8

Max Range: 0.8500. Min Range: -0.8500

Max Act: 0.6381. Min Act: -0.0003

Data Index: 1045229 (C4 (Web Text))

Max Activating Token Index: 672

Text #9

Max Range: 0.8500. Min Range: -0.8500

Max Act: 0.6568. Min Act: -0.0003

Data Index: 362194 (C4 (Web Text))

Max Activating Token Index: 101

Text #10

Max Range: 0.8500. Min Range: -0.8500

Max Act: 0.6911. Min Act: -0.0003

Data Index: 1059107 (C4 (Web Text))

Max Activating Token Index: 69

Text #11

Max Range: 0.8500. Min Range: -0.8500

Max Act: 0.5933. Min Act: -0.0003

Data Index: 915586 (C4 (Web Text))

Max Activating Token Index: 570

Text #12

Max Range: 0.8500. Min Range: -0.8500

Max Act: 0.6383. Min Act: -0.0003

Data Index: 334822 (C4 (Web Text))

Max Activating Token Index: 119

Text #13

Max Range: 0.8500. Min Range: -0.8500

Max Act: 0.6547. Min Act: -0.0003

Data Index: 646957 (C4 (Web Text))

Max Activating Token Index: 239

Text #14

Max Range: 0.8500. Min Range: -0.8500

Max Act: 0.6755. Min Act: -0.0003

Data Index: 1219005 (C4 (Web Text))

Max Activating Token Index: 213

Text #15

Max Range: 0.8500. Min Range: -0.8500

Max Act: 0.6710. Min Act: -0.0003

Data Index: 527925 (C4 (Web Text))

Max Activating Token Index: 101

Text #16

Max Range: 0.8500. Min Range: -0.8500

Max Act: 0.6733. Min Act: -0.0003

Data Index: 986410 (C4 (Web Text))

Max Activating Token Index: 340

Text #17

Max Range: 0.8500. Min Range: -0.8500

Max Act: 0.6222. Min Act: -0.0003

Data Index: 345149 (C4 (Web Text))

Max Activating Token Index: 472

Text #18

Max Range: 0.8500. Min Range: -0.8500

Max Act: 0.6191. Min Act: -0.0003

Data Index: 1315441 (C4 (Web Text))

Max Activating Token Index: 156

Text #19

Max Range: 0.8500. Min Range: -0.8500

Max Act: 0.5990. Min Act: -0.0003

Data Index: 712988 (C4 (Web Text))

Max Activating Token Index: 423