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

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

Neuron 2367 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: 0.7937. Min Range: -0.7937

Max Act: 0.7937. Min Act: -0.0003

Data Index: 1319716 (C4 (Web Text))

Max Activating Token Index: 482

Text #1

Max Range: 0.7937. Min Range: -0.7937

Max Act: 0.7588. Min Act: -0.0003

Data Index: 152269 (C4 (Web Text))

Max Activating Token Index: 53

Text #2

Max Range: 0.7937. Min Range: -0.7937

Max Act: 0.7036. Min Act: -0.0003

Data Index: 352237 (C4 (Web Text))

Max Activating Token Index: 60

Text #3

Max Range: 0.7937. Min Range: -0.7937

Max Act: 0.6591. Min Act: -0.0003

Data Index: 756635 (C4 (Web Text))

Max Activating Token Index: 152

Text #4

Max Range: 0.7937. Min Range: -0.7937

Max Act: 0.7397. Min Act: -0.0003

Data Index: 835858 (C4 (Web Text))

Max Activating Token Index: 301

Text #5

Max Range: 0.7937. Min Range: -0.7937

Max Act: 0.6758. Min Act: -0.0003

Data Index: 49041 (C4 (Web Text))

Max Activating Token Index: 82

Text #6

Max Range: 0.7937. Min Range: -0.7937

Max Act: 0.6045. Min Act: -0.0003

Data Index: 1197740 (C4 (Web Text))

Max Activating Token Index: 244

Text #7

Max Range: 0.7937. Min Range: -0.7937

Max Act: 0.6294. Min Act: -0.0003

Data Index: 1029129 (C4 (Web Text))

Max Activating Token Index: 53

Text #8

Max Range: 0.7937. Min Range: -0.7937

Max Act: 0.6328. Min Act: -0.0003

Data Index: 1026984 (C4 (Web Text))

Max Activating Token Index: 36

Text #9

Max Range: 0.7937. Min Range: -0.7937

Max Act: 0.6603. Min Act: -0.0003

Data Index: 1074085 (C4 (Web Text))

Max Activating Token Index: 274

Text #10

Max Range: 0.7937. Min Range: -0.7937

Max Act: 0.6748. Min Act: -0.0003

Data Index: 515565 (C4 (Web Text))

Max Activating Token Index: 197

Text #11

Max Range: 0.7937. Min Range: -0.7937

Max Act: 0.6310. Min Act: -0.0003

Data Index: 626255 (C4 (Web Text))

Max Activating Token Index: 16

Text #12

Max Range: 0.7937. Min Range: -0.7937

Max Act: 0.6267. Min Act: -0.0003

Data Index: 251760 (C4 (Web Text))

Max Activating Token Index: 29

Text #13

Max Range: 0.7937. Min Range: -0.7937

Max Act: 0.6453. Min Act: -0.0003

Data Index: 551968 (C4 (Web Text))

Max Activating Token Index: 83

Text #14

Max Range: 0.7937. Min Range: -0.7937

Max Act: 0.6354. Min Act: -0.0003

Data Index: 1100858 (C4 (Web Text))

Max Activating Token Index: 189

Text #15

Max Range: 0.7937. Min Range: -0.7937

Max Act: 0.5384. Min Act: -0.0003

Data Index: 498536 (C4 (Web Text))

Max Activating Token Index: 693

Text #16

Max Range: 0.7937. Min Range: -0.7937

Max Act: 0.5991. Min Act: -0.0003

Data Index: 818103 (C4 (Web Text))

Max Activating Token Index: 140

Text #17

Max Range: 0.7937. Min Range: -0.7937

Max Act: 0.5938. Min Act: -0.0003

Data Index: 390290 (C4 (Web Text))

Max Activating Token Index: 226

Text #18

Max Range: 0.7937. Min Range: -0.7937

Max Act: 0.5941. Min Act: -0.0003

Data Index: 402266 (C4 (Web Text))

Max Activating Token Index: 26

Text #19

Max Range: 0.7937. Min Range: -0.7937

Max Act: 0.6138. Min Act: -0.0003

Data Index: 999649 (C4 (Web Text))

Max Activating Token Index: 74