Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3420 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.9096. Min Range: -1.9096

Max Act: 1.8524. Min Act: -0.0001

Data Index: 193684 (C4 (Web Text))

Max Activating Token Index: 687

Text #1

Max Range: 1.9096. Min Range: -1.9096

Max Act: 1.9096. Min Act: -0.0001

Data Index: 658625 (C4 (Web Text))

Max Activating Token Index: 168

Text #2

Max Range: 1.9096. Min Range: -1.9096

Max Act: 1.7162. Min Act: -0.0001

Data Index: 17817 (C4 (Web Text))

Max Activating Token Index: 117

Text #3

Max Range: 1.9096. Min Range: -1.9096

Max Act: 1.7760. Min Act: -0.0001

Data Index: 1279563 (C4 (Web Text))

Max Activating Token Index: 966

Text #4

Max Range: 1.9096. Min Range: -1.9096

Max Act: 1.6764. Min Act: -0.0001

Data Index: 388877 (C4 (Web Text))

Max Activating Token Index: 290

Text #5

Max Range: 1.9096. Min Range: -1.9096

Max Act: 1.6661. Min Act: -0.0001

Data Index: 725825 (C4 (Web Text))

Max Activating Token Index: 855

Text #6

Max Range: 1.9096. Min Range: -1.9096

Max Act: 1.6513. Min Act: -0.0001

Data Index: 1271972 (C4 (Web Text))

Max Activating Token Index: 214

Text #7

Max Range: 1.9096. Min Range: -1.9096

Max Act: 1.6273. Min Act: -0.0000

Data Index: 591807 (C4 (Web Text))

Max Activating Token Index: 579

Text #8

Max Range: 1.9096. Min Range: -1.9096

Max Act: 1.6981. Min Act: -0.0001

Data Index: 1262504 (C4 (Web Text))

Max Activating Token Index: 209

Text #9

Max Range: 1.9096. Min Range: -1.9096

Max Act: 1.5956. Min Act: -0.0001

Data Index: 422041 (C4 (Web Text))

Max Activating Token Index: 148

Text #10

Max Range: 1.9096. Min Range: -1.9096

Max Act: 1.5408. Min Act: -0.0001

Data Index: 559896 (C4 (Web Text))

Max Activating Token Index: 813

Text #11

Max Range: 1.9096. Min Range: -1.9096

Max Act: 1.5751. Min Act: -0.0001

Data Index: 1202832 (C4 (Web Text))

Max Activating Token Index: 94

Text #12

Max Range: 1.9096. Min Range: -1.9096

Max Act: 1.5085. Min Act: -0.0001

Data Index: 629273 (C4 (Web Text))

Max Activating Token Index: 179

Text #13

Max Range: 1.9096. Min Range: -1.9096

Max Act: 1.4192. Min Act: -0.0001

Data Index: 1048127 (C4 (Web Text))

Max Activating Token Index: 886

Text #14

Max Range: 1.9096. Min Range: -1.9096

Max Act: 1.4631. Min Act: -0.0001

Data Index: 835314 (C4 (Web Text))

Max Activating Token Index: 737

Text #15

Max Range: 1.9096. Min Range: -1.9096

Max Act: 1.4561. Min Act: -0.0001

Data Index: 1166798 (C4 (Web Text))

Max Activating Token Index: 172

Text #16

Max Range: 1.9096. Min Range: -1.9096

Max Act: 1.4262. Min Act: -0.0001

Data Index: 968701 (C4 (Web Text))

Max Activating Token Index: 1011

Text #17

Max Range: 1.9096. Min Range: -1.9096

Max Act: 1.4239. Min Act: -0.0001

Data Index: 229857 (C4 (Web Text))

Max Activating Token Index: 101

Text #18

Max Range: 1.9096. Min Range: -1.9096

Max Act: 1.4809. Min Act: -0.0001

Data Index: 1134013 (C4 (Web Text))

Max Activating Token Index: 981

Text #19

Max Range: 1.9096. Min Range: -1.9096

Max Act: 1.4382. Min Act: -0.0001

Data Index: 370376 (C4 (Web Text))

Max Activating Token Index: 551