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

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

Neuron 1512 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1302. Min Range: -1.1302

Max Act: 1.1302. Min Act: -0.0001

Data Index: 1126941 (C4 (Web Text))

Max Activating Token Index: 665

Text #1

Max Range: 1.1302. Min Range: -1.1302

Max Act: 1.1015. Min Act: -0.0001

Data Index: 1033574 (C4 (Web Text))

Max Activating Token Index: 128

Text #2

Max Range: 1.1302. Min Range: -1.1302

Max Act: 1.0484. Min Act: -0.0001

Data Index: 408213 (C4 (Web Text))

Max Activating Token Index: 45

Text #3

Max Range: 1.1302. Min Range: -1.1302

Max Act: 1.0531. Min Act: -0.0001

Data Index: 1056686 (C4 (Web Text))

Max Activating Token Index: 877

Text #4

Max Range: 1.1302. Min Range: -1.1302

Max Act: 1.0488. Min Act: -0.0001

Data Index: 883310 (C4 (Web Text))

Max Activating Token Index: 809

Text #5

Max Range: 1.1302. Min Range: -1.1302

Max Act: 1.0311. Min Act: -0.0001

Data Index: 306386 (C4 (Web Text))

Max Activating Token Index: 412

Text #6

Max Range: 1.1302. Min Range: -1.1302

Max Act: 0.9585. Min Act: -0.0001

Data Index: 559436 (C4 (Web Text))

Max Activating Token Index: 693

Text #7

Max Range: 1.1302. Min Range: -1.1302

Max Act: 1.0578. Min Act: -0.0001

Data Index: 209746 (C4 (Web Text))

Max Activating Token Index: 339

Text #8

Max Range: 1.1302. Min Range: -1.1302

Max Act: 1.0096. Min Act: -0.0001

Data Index: 77290 (C4 (Web Text))

Max Activating Token Index: 254

Text #9

Max Range: 1.1302. Min Range: -1.1302

Max Act: 0.9987. Min Act: -0.0001

Data Index: 608652 (C4 (Web Text))

Max Activating Token Index: 125

Text #10

Max Range: 1.1302. Min Range: -1.1302

Max Act: 0.9276. Min Act: -0.0001

Data Index: 971682 (C4 (Web Text))

Max Activating Token Index: 217

Text #11

Max Range: 1.1302. Min Range: -1.1302

Max Act: 1.0267. Min Act: -0.0001

Data Index: 154409 (C4 (Web Text))

Max Activating Token Index: 722

Text #12

Max Range: 1.1302. Min Range: -1.1302

Max Act: 0.9355. Min Act: -0.0001

Data Index: 965691 (C4 (Web Text))

Max Activating Token Index: 160

Text #13

Max Range: 1.1302. Min Range: -1.1302

Max Act: 0.9354. Min Act: -0.0001

Data Index: 57954 (C4 (Web Text))

Max Activating Token Index: 87

Text #14

Max Range: 1.1302. Min Range: -1.1302

Max Act: 1.0647. Min Act: -0.0001

Data Index: 1281106 (C4 (Web Text))

Max Activating Token Index: 94

Text #15

Max Range: 1.1302. Min Range: -1.1302

Max Act: 1.0097. Min Act: -0.0001

Data Index: 155289 (C4 (Web Text))

Max Activating Token Index: 916

Text #16

Max Range: 1.1302. Min Range: -1.1302

Max Act: 0.8871. Min Act: -0.0001

Data Index: 1147373 (C4 (Web Text))

Max Activating Token Index: 377

Text #17

Max Range: 1.1302. Min Range: -1.1302

Max Act: 0.8766. Min Act: -0.0001

Data Index: 333008 (C4 (Web Text))

Max Activating Token Index: 72

Text #18

Max Range: 1.1302. Min Range: -1.1302

Max Act: 0.8237. Min Act: -0.0001

Data Index: 517684 (C4 (Web Text))

Max Activating Token Index: 550

Text #19

Max Range: 1.1302. Min Range: -1.1302

Max Act: 0.8854. Min Act: -0.0001

Data Index: 776498 (C4 (Web Text))

Max Activating Token Index: 662