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

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

Neuron 3953 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: 3.1024. Min Range: -3.1024

Max Act: 3.1024. Min Act: -0.0000

Data Index: 1289591 (C4 (Web Text))

Max Activating Token Index: 328

Text #1

Max Range: 3.1024. Min Range: -3.1024

Max Act: 2.2450. Min Act: -0.0000

Data Index: 608294 (C4 (Web Text))

Max Activating Token Index: 919

Text #2

Max Range: 3.1024. Min Range: -3.1024

Max Act: 2.2423. Min Act: -0.0000

Data Index: 934852 (C4 (Web Text))

Max Activating Token Index: 541

Text #3

Max Range: 3.1024. Min Range: -3.1024

Max Act: 2.1322. Min Act: -0.0000

Data Index: 1246293 (C4 (Web Text))

Max Activating Token Index: 946

Text #4

Max Range: 3.1024. Min Range: -3.1024

Max Act: 2.0981. Min Act: -0.0000

Data Index: 749310 (C4 (Web Text))

Max Activating Token Index: 219

Text #5

Max Range: 3.1024. Min Range: -3.1024

Max Act: 2.0264. Min Act: -0.0000

Data Index: 625311 (C4 (Web Text))

Max Activating Token Index: 108

Text #6

Max Range: 3.1024. Min Range: -3.1024

Max Act: 2.0643. Min Act: -0.0000

Data Index: 588471 (C4 (Web Text))

Max Activating Token Index: 383

Text #7

Max Range: 3.1024. Min Range: -3.1024

Max Act: 1.9512. Min Act: -0.0000

Data Index: 76339 (C4 (Web Text))

Max Activating Token Index: 656

Text #8

Max Range: 3.1024. Min Range: -3.1024

Max Act: 2.0387. Min Act: -0.0000

Data Index: 957692 (C4 (Web Text))

Max Activating Token Index: 533

Text #9

Max Range: 3.1024. Min Range: -3.1024

Max Act: 1.9558. Min Act: -0.0000

Data Index: 152204 (C4 (Web Text))

Max Activating Token Index: 127

Text #10

Max Range: 3.1024. Min Range: -3.1024

Max Act: 1.9404. Min Act: -0.0000

Data Index: 1103919 (C4 (Web Text))

Max Activating Token Index: 894

Text #11

Max Range: 3.1024. Min Range: -3.1024

Max Act: 1.9188. Min Act: -0.0000

Data Index: 237048 (C4 (Web Text))

Max Activating Token Index: 449

Text #12

Max Range: 3.1024. Min Range: -3.1024

Max Act: 2.0018. Min Act: -0.0000

Data Index: 637870 (C4 (Web Text))

Max Activating Token Index: 439

Text #13

Max Range: 3.1024. Min Range: -3.1024

Max Act: 2.0219. Min Act: -0.0000

Data Index: 1340552 (C4 (Web Text))

Max Activating Token Index: 466

Text #14

Max Range: 3.1024. Min Range: -3.1024

Max Act: 1.9624. Min Act: -0.0000

Data Index: 848486 (C4 (Web Text))

Max Activating Token Index: 780

Text #15

Max Range: 3.1024. Min Range: -3.1024

Max Act: 1.9390. Min Act: -0.0000

Data Index: 1132221 (C4 (Web Text))

Max Activating Token Index: 884

Text #16

Max Range: 3.1024. Min Range: -3.1024

Max Act: 1.9435. Min Act: -0.0000

Data Index: 1061836 (C4 (Web Text))

Max Activating Token Index: 467

Text #17

Max Range: 3.1024. Min Range: -3.1024

Max Act: 1.9321. Min Act: -0.0000

Data Index: 961525 (C4 (Web Text))

Max Activating Token Index: 764

Text #18

Max Range: 3.1024. Min Range: -3.1024

Max Act: 1.8701. Min Act: -0.0000

Data Index: 246877 (C4 (Web Text))

Max Activating Token Index: 634

Text #19

Max Range: 3.1024. Min Range: -3.1024

Max Act: 1.9690. Min Act: -0.0000

Data Index: 1179241 (C4 (Web Text))

Max Activating Token Index: 193