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

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

Neuron 810 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.0314. Min Range: -7.0314

Max Act: 7.0314. Min Act: -0.0000

Data Index: 2692 (C4 (Web Text))

Max Activating Token Index: 12

Text #1

Max Range: 7.0314. Min Range: -7.0314

Max Act: 6.6000. Min Act: -0.0001

Data Index: 21080 (C4 (Web Text))

Max Activating Token Index: 864

Text #2

Max Range: 7.0314. Min Range: -7.0314

Max Act: 6.4427. Min Act: -0.0000

Data Index: 57370 (C4 (Web Text))

Max Activating Token Index: 43

Text #3

Max Range: 7.0314. Min Range: -7.0314

Max Act: 6.6374. Min Act: -0.0001

Data Index: 983721 (C4 (Web Text))

Max Activating Token Index: 286

Text #4

Max Range: 7.0314. Min Range: -7.0314

Max Act: 6.4193. Min Act: -0.0000

Data Index: 851733 (C4 (Web Text))

Max Activating Token Index: 92

Text #5

Max Range: 7.0314. Min Range: -7.0314

Max Act: 6.5997. Min Act: -0.0000

Data Index: 1150240 (C4 (Web Text))

Max Activating Token Index: 507

Text #6

Max Range: 7.0314. Min Range: -7.0314

Max Act: 6.4164. Min Act: -0.0001

Data Index: 912580 (C4 (Web Text))

Max Activating Token Index: 166

Text #7

Max Range: 7.0314. Min Range: -7.0314

Max Act: 6.3941. Min Act: -0.0000

Data Index: 1168356 (C4 (Web Text))

Max Activating Token Index: 346

Text #8

Max Range: 7.0314. Min Range: -7.0314

Max Act: 6.4026. Min Act: -0.0000

Data Index: 13697 (C4 (Web Text))

Max Activating Token Index: 892

Text #9

Max Range: 7.0314. Min Range: -7.0314

Max Act: 6.3606. Min Act: -0.0000

Data Index: 1093389 (C4 (Web Text))

Max Activating Token Index: 454

Text #10

Max Range: 7.0314. Min Range: -7.0314

Max Act: 6.1162. Min Act: -0.0000

Data Index: 65318 (C4 (Web Text))

Max Activating Token Index: 914

Text #11

Max Range: 7.0314. Min Range: -7.0314

Max Act: 6.2926. Min Act: -0.0000

Data Index: 209206 (C4 (Web Text))

Max Activating Token Index: 485

Text #12

Max Range: 7.0314. Min Range: -7.0314

Max Act: 6.4722. Min Act: -0.0000

Data Index: 214137 (C4 (Web Text))

Max Activating Token Index: 506

Text #13

Max Range: 7.0314. Min Range: -7.0314

Max Act: 5.8341. Min Act: -0.0001

Data Index: 1008685 (C4 (Web Text))

Max Activating Token Index: 483

Text #14

Max Range: 7.0314. Min Range: -7.0314

Max Act: 6.1462. Min Act: -0.0000

Data Index: 881547 (C4 (Web Text))

Max Activating Token Index: 655

Text #15

Max Range: 7.0314. Min Range: -7.0314

Max Act: 6.1614. Min Act: -0.0001

Data Index: 1208258 (C4 (Web Text))

Max Activating Token Index: 862

Text #16

Max Range: 7.0314. Min Range: -7.0314

Max Act: 6.3080. Min Act: -0.0001

Data Index: 1241851 (C4 (Web Text))

Max Activating Token Index: 303

Text #17

Max Range: 7.0314. Min Range: -7.0314

Max Act: 6.1334. Min Act: -0.0001

Data Index: 1228409 (C4 (Web Text))

Max Activating Token Index: 236

Text #18

Max Range: 7.0314. Min Range: -7.0314

Max Act: 6.1446. Min Act: -0.0000

Data Index: 158098 (C4 (Web Text))

Max Activating Token Index: 649

Text #19

Max Range: 7.0314. Min Range: -7.0314

Max Act: 5.9082. Min Act: -0.0000

Data Index: 54002 (C4 (Web Text))

Max Activating Token Index: 795