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

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

Neuron 5636 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: 1.0170. Min Range: -1.0170

Max Act: 1.0170. Min Act: -0.0000

Data Index: 520443 (C4 (Web Text))

Max Activating Token Index: 602

Text #1

Max Range: 1.0170. Min Range: -1.0170

Max Act: 0.8934. Min Act: -0.0000

Data Index: 175221 (C4 (Web Text))

Max Activating Token Index: 854

Text #2

Max Range: 1.0170. Min Range: -1.0170

Max Act: 0.8866. Min Act: -0.0000

Data Index: 174361 (C4 (Web Text))

Max Activating Token Index: 104

Text #3

Max Range: 1.0170. Min Range: -1.0170

Max Act: 0.8782. Min Act: -0.0000

Data Index: 1115665 (C4 (Web Text))

Max Activating Token Index: 108

Text #4

Max Range: 1.0170. Min Range: -1.0170

Max Act: 0.9300. Min Act: -0.0000

Data Index: 218259 (C4 (Web Text))

Max Activating Token Index: 199

Text #5

Max Range: 1.0170. Min Range: -1.0170

Max Act: 0.9090. Min Act: -0.0000

Data Index: 535042 (C4 (Web Text))

Max Activating Token Index: 271

Text #6

Max Range: 1.0170. Min Range: -1.0170

Max Act: 0.8805. Min Act: -0.0000

Data Index: 167562 (C4 (Web Text))

Max Activating Token Index: 13

Text #7

Max Range: 1.0170. Min Range: -1.0170

Max Act: 0.8475. Min Act: -0.0000

Data Index: 809418 (C4 (Web Text))

Max Activating Token Index: 183

Text #8

Max Range: 1.0170. Min Range: -1.0170

Max Act: 0.8226. Min Act: -0.0000

Data Index: 1038566 (C4 (Web Text))

Max Activating Token Index: 50

Text #9

Max Range: 1.0170. Min Range: -1.0170

Max Act: 0.8033. Min Act: -0.0000

Data Index: 831311 (C4 (Web Text))

Max Activating Token Index: 913

Text #10

Max Range: 1.0170. Min Range: -1.0170

Max Act: 0.8314. Min Act: -0.0000

Data Index: 890828 (C4 (Web Text))

Max Activating Token Index: 522

Text #11

Max Range: 1.0170. Min Range: -1.0170

Max Act: 0.7825. Min Act: -0.0000

Data Index: 1237783 (C4 (Web Text))

Max Activating Token Index: 524

Text #12

Max Range: 1.0170. Min Range: -1.0170

Max Act: 0.8043. Min Act: -0.0000

Data Index: 128449 (C4 (Web Text))

Max Activating Token Index: 547

Text #13

Max Range: 1.0170. Min Range: -1.0170

Max Act: 0.7764. Min Act: -0.0000

Data Index: 220702 (C4 (Web Text))

Max Activating Token Index: 458

Text #14

Max Range: 1.0170. Min Range: -1.0170

Max Act: 0.8182. Min Act: -0.0000

Data Index: 243522 (C4 (Web Text))

Max Activating Token Index: 912

Text #15

Max Range: 1.0170. Min Range: -1.0170

Max Act: 0.7695. Min Act: -0.0000

Data Index: 671541 (C4 (Web Text))

Max Activating Token Index: 1018

Text #16

Max Range: 1.0170. Min Range: -1.0170

Max Act: 0.8117. Min Act: -0.0000

Data Index: 1019932 (C4 (Web Text))

Max Activating Token Index: 697

Text #17

Max Range: 1.0170. Min Range: -1.0170

Max Act: 0.7908. Min Act: -0.0000

Data Index: 1200389 (C4 (Web Text))

Max Activating Token Index: 24

Text #18

Max Range: 1.0170. Min Range: -1.0170

Max Act: 0.7537. Min Act: -0.0000

Data Index: 57804 (C4 (Web Text))

Max Activating Token Index: 869

Text #19

Max Range: 1.0170. Min Range: -1.0170

Max Act: 0.7584. Min Act: -0.0000

Data Index: 497127 (C4 (Web Text))

Max Activating Token Index: 87