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

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

Neuron 5398 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8067. Min Range: -0.8067

Max Act: 0.8067. Min Act: 0.0000

Data Index: 990164 (C4 (Web Text))

Max Activating Token Index: 365

Text #1

Max Range: 0.8067. Min Range: -0.8067

Max Act: 0.7996. Min Act: -0.0000

Data Index: 733682 (C4 (Web Text))

Max Activating Token Index: 381

Text #2

Max Range: 0.8067. Min Range: -0.8067

Max Act: 0.6568. Min Act: -0.0000

Data Index: 747065 (C4 (Web Text))

Max Activating Token Index: 279

Text #3

Max Range: 0.8067. Min Range: -0.8067

Max Act: 0.6141. Min Act: 0.0000

Data Index: 926864 (C4 (Web Text))

Max Activating Token Index: 69

Text #4

Max Range: 0.8067. Min Range: -0.8067

Max Act: 0.6155. Min Act: -0.0000

Data Index: 898088 (C4 (Web Text))

Max Activating Token Index: 492

Text #5

Max Range: 0.8067. Min Range: -0.8067

Max Act: 0.5504. Min Act: 0.0000

Data Index: 696052 (C4 (Web Text))

Max Activating Token Index: 665

Text #6

Max Range: 0.8067. Min Range: -0.8067

Max Act: 0.5240. Min Act: -0.0000

Data Index: 860563 (C4 (Web Text))

Max Activating Token Index: 302

Text #7

Max Range: 0.8067. Min Range: -0.8067

Max Act: 0.5851. Min Act: -0.0000

Data Index: 1190636 (C4 (Web Text))

Max Activating Token Index: 88

Text #8

Max Range: 0.8067. Min Range: -0.8067

Max Act: 0.5719. Min Act: -0.0000

Data Index: 1132680 (C4 (Web Text))

Max Activating Token Index: 249

Text #9

Max Range: 0.8067. Min Range: -0.8067

Max Act: 0.5265. Min Act: -0.0000

Data Index: 1224672 (C4 (Web Text))

Max Activating Token Index: 518

Text #10

Max Range: 0.8067. Min Range: -0.8067

Max Act: 0.5822. Min Act: -0.0000

Data Index: 1110533 (C4 (Web Text))

Max Activating Token Index: 144

Text #11

Max Range: 0.8067. Min Range: -0.8067

Max Act: 0.5183. Min Act: -0.0000

Data Index: 1019768 (C4 (Web Text))

Max Activating Token Index: 536

Text #12

Max Range: 0.8067. Min Range: -0.8067

Max Act: 0.4979. Min Act: -0.0000

Data Index: 726235 (C4 (Web Text))

Max Activating Token Index: 311

Text #13

Max Range: 0.8067. Min Range: -0.8067

Max Act: 0.5230. Min Act: -0.0000

Data Index: 204786 (C4 (Web Text))

Max Activating Token Index: 350

Text #14

Max Range: 0.8067. Min Range: -0.8067

Max Act: 0.4752. Min Act: -0.0000

Data Index: 262573 (C4 (Web Text))

Max Activating Token Index: 359

Text #15

Max Range: 0.8067. Min Range: -0.8067

Max Act: 0.4975. Min Act: -0.0000

Data Index: 341237 (C4 (Web Text))

Max Activating Token Index: 725

Text #16

Max Range: 0.8067. Min Range: -0.8067

Max Act: 0.4999. Min Act: -0.0000

Data Index: 143578 (C4 (Web Text))

Max Activating Token Index: 39

Text #17

Max Range: 0.8067. Min Range: -0.8067

Max Act: 0.4983. Min Act: -0.0000

Data Index: 381217 (C4 (Web Text))

Max Activating Token Index: 26

Text #18

Max Range: 0.8067. Min Range: -0.8067

Max Act: 0.5008. Min Act: -0.0000

Data Index: 1024121 (C4 (Web Text))

Max Activating Token Index: 508

Text #19

Max Range: 0.8067. Min Range: -0.8067

Max Act: 0.5156. Min Act: -0.0000

Data Index: 1086997 (C4 (Web Text))

Max Activating Token Index: 171