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

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

Neuron 3767 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8690. Min Range: -0.8690

Max Act: 0.8690. Min Act: -0.0000

Data Index: 733156 (C4 (Web Text))

Max Activating Token Index: 39

Text #1

Max Range: 0.8690. Min Range: -0.8690

Max Act: 0.7739. Min Act: -0.0000

Data Index: 1342319 (C4 (Web Text))

Max Activating Token Index: 312

Text #2

Max Range: 0.8690. Min Range: -0.8690

Max Act: 0.8612. Min Act: -0.0000

Data Index: 810027 (C4 (Web Text))

Max Activating Token Index: 169

Text #3

Max Range: 0.8690. Min Range: -0.8690

Max Act: 0.7298. Min Act: -0.0000

Data Index: 406818 (C4 (Web Text))

Max Activating Token Index: 205

Text #4

Max Range: 0.8690. Min Range: -0.8690

Max Act: 0.8069. Min Act: -0.0000

Data Index: 420697 (C4 (Web Text))

Max Activating Token Index: 646

Text #5

Max Range: 0.8690. Min Range: -0.8690

Max Act: 0.7219. Min Act: -0.0000

Data Index: 1595010 (Python Code)

Max Activating Token Index: 171

Text #6

Max Range: 0.8690. Min Range: -0.8690

Max Act: 0.6926. Min Act: -0.0000

Data Index: 1121041 (C4 (Web Text))

Max Activating Token Index: 230

Text #7

Max Range: 0.8690. Min Range: -0.8690

Max Act: 0.7347. Min Act: -0.0000

Data Index: 411832 (C4 (Web Text))

Max Activating Token Index: 958

Text #8

Max Range: 0.8690. Min Range: -0.8690

Max Act: 0.6901. Min Act: -0.0000

Data Index: 863699 (C4 (Web Text))

Max Activating Token Index: 158

Text #9

Max Range: 0.8690. Min Range: -0.8690

Max Act: 0.6832. Min Act: -0.0000

Data Index: 1023815 (C4 (Web Text))

Max Activating Token Index: 306

Text #10

Max Range: 0.8690. Min Range: -0.8690

Max Act: 0.5800. Min Act: -0.0000

Data Index: 928942 (C4 (Web Text))

Max Activating Token Index: 476

Text #11

Max Range: 0.8690. Min Range: -0.8690

Max Act: 0.6202. Min Act: -0.0000

Data Index: 675656 (C4 (Web Text))

Max Activating Token Index: 19

Text #12

Max Range: 0.8690. Min Range: -0.8690

Max Act: 0.6761. Min Act: -0.0000

Data Index: 273508 (C4 (Web Text))

Max Activating Token Index: 13

Text #13

Max Range: 0.8690. Min Range: -0.8690

Max Act: 0.6367. Min Act: -0.0000

Data Index: 565290 (C4 (Web Text))

Max Activating Token Index: 177

Text #14

Max Range: 0.8690. Min Range: -0.8690

Max Act: 0.6050. Min Act: -0.0000

Data Index: 427307 (C4 (Web Text))

Max Activating Token Index: 28

Text #15

Max Range: 0.8690. Min Range: -0.8690

Max Act: 0.6888. Min Act: -0.0000

Data Index: 1470917 (Python Code)

Max Activating Token Index: 496

Text #16

Max Range: 0.8690. Min Range: -0.8690

Max Act: 0.6552. Min Act: -0.0000

Data Index: 1280529 (C4 (Web Text))

Max Activating Token Index: 840

Text #17

Max Range: 0.8690. Min Range: -0.8690

Max Act: 0.5667. Min Act: -0.0000

Data Index: 686100 (C4 (Web Text))

Max Activating Token Index: 453

Text #18

Max Range: 0.8690. Min Range: -0.8690

Max Act: 0.6050. Min Act: -0.0000

Data Index: 888820 (C4 (Web Text))

Max Activating Token Index: 220

Text #19

Max Range: 0.8690. Min Range: -0.8690

Max Act: 0.6044. Min Act: -0.0000

Data Index: 3256 (C4 (Web Text))

Max Activating Token Index: 247