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

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

Neuron 1463 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9992. Min Range: -0.9992

Max Act: 0.9992. Min Act: 0.0000

Data Index: 58676 (C4 (Web Text))

Max Activating Token Index: 379

Text #1

Max Range: 0.9992. Min Range: -0.9992

Max Act: 0.9372. Min Act: -0.0000

Data Index: 302953 (C4 (Web Text))

Max Activating Token Index: 831

Text #2

Max Range: 0.9992. Min Range: -0.9992

Max Act: 0.8564. Min Act: 0.0000

Data Index: 257541 (C4 (Web Text))

Max Activating Token Index: 307

Text #3

Max Range: 0.9992. Min Range: -0.9992

Max Act: 0.7705. Min Act: 0.0000

Data Index: 432846 (C4 (Web Text))

Max Activating Token Index: 90

Text #4

Max Range: 0.9992. Min Range: -0.9992

Max Act: 0.8050. Min Act: 0.0000

Data Index: 380712 (C4 (Web Text))

Max Activating Token Index: 219

Text #5

Max Range: 0.9992. Min Range: -0.9992

Max Act: 0.7622. Min Act: 0.0000

Data Index: 135206 (C4 (Web Text))

Max Activating Token Index: 70

Text #6

Max Range: 0.9992. Min Range: -0.9992

Max Act: 0.7715. Min Act: -0.0000

Data Index: 375566 (C4 (Web Text))

Max Activating Token Index: 951

Text #7

Max Range: 0.9992. Min Range: -0.9992

Max Act: 0.7767. Min Act: -0.0000

Data Index: 1237295 (C4 (Web Text))

Max Activating Token Index: 374

Text #8

Max Range: 0.9992. Min Range: -0.9992

Max Act: 0.7068. Min Act: -0.0000

Data Index: 130373 (C4 (Web Text))

Max Activating Token Index: 338

Text #9

Max Range: 0.9992. Min Range: -0.9992

Max Act: 0.6800. Min Act: -0.0000

Data Index: 1002883 (C4 (Web Text))

Max Activating Token Index: 794

Text #10

Max Range: 0.9992. Min Range: -0.9992

Max Act: 0.6396. Min Act: -0.0000

Data Index: 989832 (C4 (Web Text))

Max Activating Token Index: 912

Text #11

Max Range: 0.9992. Min Range: -0.9992

Max Act: 0.6941. Min Act: -0.0000

Data Index: 1309280 (C4 (Web Text))

Max Activating Token Index: 988

Text #12

Max Range: 0.9992. Min Range: -0.9992

Max Act: 0.6550. Min Act: 0.0000

Data Index: 32897 (C4 (Web Text))

Max Activating Token Index: 26

Text #13

Max Range: 0.9992. Min Range: -0.9992

Max Act: 0.6164. Min Act: -0.0000

Data Index: 660784 (C4 (Web Text))

Max Activating Token Index: 124

Text #14

Max Range: 0.9992. Min Range: -0.9992

Max Act: 0.5739. Min Act: -0.0000

Data Index: 823647 (C4 (Web Text))

Max Activating Token Index: 438

Text #15

Max Range: 0.9992. Min Range: -0.9992

Max Act: 0.5916. Min Act: -0.0000

Data Index: 674959 (C4 (Web Text))

Max Activating Token Index: 189

Text #16

Max Range: 0.9992. Min Range: -0.9992

Max Act: 0.5406. Min Act: -0.0000

Data Index: 468562 (C4 (Web Text))

Max Activating Token Index: 894

Text #17

Max Range: 0.9992. Min Range: -0.9992

Max Act: 0.5750. Min Act: -0.0000

Data Index: 952150 (C4 (Web Text))

Max Activating Token Index: 617

Text #18

Max Range: 0.9992. Min Range: -0.9992

Max Act: 0.5343. Min Act: -0.0000

Data Index: 183570 (C4 (Web Text))

Max Activating Token Index: 302

Text #19

Max Range: 0.9992. Min Range: -0.9992

Max Act: 0.5423. Min Act: -0.0000

Data Index: 680674 (C4 (Web Text))

Max Activating Token Index: 973