Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 232 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.7734. Min Range: -0.7734

Max Act: 0.7734. Min Act: 0.0000

Data Index: 87028 (C4 (Web Text))

Max Activating Token Index: 455

Text #1

Max Range: 0.7734. Min Range: -0.7734

Max Act: 0.7692. Min Act: 0.0000

Data Index: 1053326 (C4 (Web Text))

Max Activating Token Index: 485

Text #2

Max Range: 0.7734. Min Range: -0.7734

Max Act: 0.7267. Min Act: -0.0000

Data Index: 899480 (C4 (Web Text))

Max Activating Token Index: 232

Text #3

Max Range: 0.7734. Min Range: -0.7734

Max Act: 0.7133. Min Act: -0.0000

Data Index: 167990 (C4 (Web Text))

Max Activating Token Index: 926

Text #4

Max Range: 0.7734. Min Range: -0.7734

Max Act: 0.7294. Min Act: -0.0000

Data Index: 143867 (C4 (Web Text))

Max Activating Token Index: 895

Text #5

Max Range: 0.7734. Min Range: -0.7734

Max Act: 0.7599. Min Act: -0.0000

Data Index: 617366 (C4 (Web Text))

Max Activating Token Index: 150

Text #6

Max Range: 0.7734. Min Range: -0.7734

Max Act: 0.7039. Min Act: -0.0000

Data Index: 1326706 (C4 (Web Text))

Max Activating Token Index: 720

Text #7

Max Range: 0.7734. Min Range: -0.7734

Max Act: 0.6842. Min Act: -0.0000

Data Index: 264827 (C4 (Web Text))

Max Activating Token Index: 490

Text #8

Max Range: 0.7734. Min Range: -0.7734

Max Act: 0.6038. Min Act: -0.0000

Data Index: 769285 (C4 (Web Text))

Max Activating Token Index: 108

Text #9

Max Range: 0.7734. Min Range: -0.7734

Max Act: 0.5848. Min Act: -0.0000

Data Index: 1133475 (C4 (Web Text))

Max Activating Token Index: 49

Text #10

Max Range: 0.7734. Min Range: -0.7734

Max Act: 0.6560. Min Act: -0.0000

Data Index: 1337045 (C4 (Web Text))

Max Activating Token Index: 494

Text #11

Max Range: 0.7734. Min Range: -0.7734

Max Act: 0.6897. Min Act: 0.0000

Data Index: 887420 (C4 (Web Text))

Max Activating Token Index: 638

Text #12

Max Range: 0.7734. Min Range: -0.7734

Max Act: 0.6477. Min Act: 0.0000

Data Index: 646915 (C4 (Web Text))

Max Activating Token Index: 666

Text #13

Max Range: 0.7734. Min Range: -0.7734

Max Act: 0.6216. Min Act: -0.0000

Data Index: 365848 (C4 (Web Text))

Max Activating Token Index: 787

Text #14

Max Range: 0.7734. Min Range: -0.7734

Max Act: 0.6165. Min Act: -0.0000

Data Index: 205848 (C4 (Web Text))

Max Activating Token Index: 864

Text #15

Max Range: 0.7734. Min Range: -0.7734

Max Act: 0.6155. Min Act: -0.0000

Data Index: 828881 (C4 (Web Text))

Max Activating Token Index: 680

Text #16

Max Range: 0.7734. Min Range: -0.7734

Max Act: 0.6777. Min Act: -0.0000

Data Index: 571683 (C4 (Web Text))

Max Activating Token Index: 106

Text #17

Max Range: 0.7734. Min Range: -0.7734

Max Act: 0.6181. Min Act: -0.0000

Data Index: 1213981 (C4 (Web Text))

Max Activating Token Index: 644

Text #18

Max Range: 0.7734. Min Range: -0.7734

Max Act: 0.6310. Min Act: 0.0000

Data Index: 477407 (C4 (Web Text))

Max Activating Token Index: 238

Text #19

Max Range: 0.7734. Min Range: -0.7734

Max Act: 0.6844. Min Act: -0.0000

Data Index: 1340216 (C4 (Web Text))

Max Activating Token Index: 765