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

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

Neuron 192 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.3362. Min Range: -5.3362

Max Act: 5.3362. Min Act: -0.0000

Data Index: 583019 (C4 (Web Text))

Max Activating Token Index: 318

Text #1

Max Range: 5.3362. Min Range: -5.3362

Max Act: 3.7634. Min Act: -0.0000

Data Index: 46161 (C4 (Web Text))

Max Activating Token Index: 765

Text #2

Max Range: 5.3362. Min Range: -5.3362

Max Act: 4.0285. Min Act: -0.0000

Data Index: 1335582 (C4 (Web Text))

Max Activating Token Index: 866

Text #3

Max Range: 5.3362. Min Range: -5.3362

Max Act: 3.3672. Min Act: -0.0000

Data Index: 1178136 (C4 (Web Text))

Max Activating Token Index: 402

Text #4

Max Range: 5.3362. Min Range: -5.3362

Max Act: 3.5104. Min Act: -0.0000

Data Index: 1238527 (C4 (Web Text))

Max Activating Token Index: 150

Text #5

Max Range: 5.3362. Min Range: -5.3362

Max Act: 3.5253. Min Act: -0.0000

Data Index: 107124 (C4 (Web Text))

Max Activating Token Index: 389

Text #6

Max Range: 5.3362. Min Range: -5.3362

Max Act: 3.1400. Min Act: -0.0000

Data Index: 245259 (C4 (Web Text))

Max Activating Token Index: 171

Text #7

Max Range: 5.3362. Min Range: -5.3362

Max Act: 3.2671. Min Act: -0.0000

Data Index: 1194863 (C4 (Web Text))

Max Activating Token Index: 615

Text #8

Max Range: 5.3362. Min Range: -5.3362

Max Act: 3.2651. Min Act: -0.0000

Data Index: 7854 (C4 (Web Text))

Max Activating Token Index: 84

Text #9

Max Range: 5.3362. Min Range: -5.3362

Max Act: 3.2435. Min Act: -0.0000

Data Index: 680703 (C4 (Web Text))

Max Activating Token Index: 307

Text #10

Max Range: 5.3362. Min Range: -5.3362

Max Act: 3.2662. Min Act: -0.0000

Data Index: 1040808 (C4 (Web Text))

Max Activating Token Index: 48

Text #11

Max Range: 5.3362. Min Range: -5.3362

Max Act: 3.3781. Min Act: -0.0000

Data Index: 332473 (C4 (Web Text))

Max Activating Token Index: 851

Text #12

Max Range: 5.3362. Min Range: -5.3362

Max Act: 3.0430. Min Act: -0.0000

Data Index: 1307733 (C4 (Web Text))

Max Activating Token Index: 452

Text #13

Max Range: 5.3362. Min Range: -5.3362

Max Act: 2.4666. Min Act: -0.0000

Data Index: 585470 (C4 (Web Text))

Max Activating Token Index: 843

Text #14

Max Range: 5.3362. Min Range: -5.3362

Max Act: 2.9922. Min Act: -0.0000

Data Index: 468787 (C4 (Web Text))

Max Activating Token Index: 694

Text #15

Max Range: 5.3362. Min Range: -5.3362

Max Act: 3.1093. Min Act: -0.0000

Data Index: 320599 (C4 (Web Text))

Max Activating Token Index: 949

Text #16

Max Range: 5.3362. Min Range: -5.3362

Max Act: 3.0205. Min Act: -0.0000

Data Index: 204708 (C4 (Web Text))

Max Activating Token Index: 452

Text #17

Max Range: 5.3362. Min Range: -5.3362

Max Act: 2.8408. Min Act: -0.0000

Data Index: 529855 (C4 (Web Text))

Max Activating Token Index: 818

Text #18

Max Range: 5.3362. Min Range: -5.3362

Max Act: 2.9898. Min Act: -0.0000

Data Index: 935001 (C4 (Web Text))

Max Activating Token Index: 982

Text #19

Max Range: 5.3362. Min Range: -5.3362

Max Act: 3.0164. Min Act: -0.0000

Data Index: 1243791 (C4 (Web Text))

Max Activating Token Index: 833