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

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

Neuron 932 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5971. Min Range: -3.5971

Max Act: 3.5971. Min Act: -0.0000

Data Index: 1207782 (C4 (Web Text))

Max Activating Token Index: 592

Text #1

Max Range: 3.5971. Min Range: -3.5971

Max Act: 2.6999. Min Act: -0.0000

Data Index: 808689 (C4 (Web Text))

Max Activating Token Index: 478

Text #2

Max Range: 3.5971. Min Range: -3.5971

Max Act: 2.5194. Min Act: -0.0000

Data Index: 603993 (C4 (Web Text))

Max Activating Token Index: 155

Text #3

Max Range: 3.5971. Min Range: -3.5971

Max Act: 2.3528. Min Act: -0.0000

Data Index: 414190 (C4 (Web Text))

Max Activating Token Index: 139

Text #4

Max Range: 3.5971. Min Range: -3.5971

Max Act: 2.5786. Min Act: -0.0000

Data Index: 1321151 (C4 (Web Text))

Max Activating Token Index: 378

Text #5

Max Range: 3.5971. Min Range: -3.5971

Max Act: 2.4050. Min Act: -0.0000

Data Index: 548971 (C4 (Web Text))

Max Activating Token Index: 554

Text #6

Max Range: 3.5971. Min Range: -3.5971

Max Act: 2.2928. Min Act: -0.0000

Data Index: 1234654 (C4 (Web Text))

Max Activating Token Index: 481

Text #7

Max Range: 3.5971. Min Range: -3.5971

Max Act: 2.3663. Min Act: -0.0000

Data Index: 97038 (C4 (Web Text))

Max Activating Token Index: 940

Text #8

Max Range: 3.5971. Min Range: -3.5971

Max Act: 2.1086. Min Act: -0.0000

Data Index: 1146478 (C4 (Web Text))

Max Activating Token Index: 839

Text #9

Max Range: 3.5971. Min Range: -3.5971

Max Act: 2.2044. Min Act: -0.0000

Data Index: 1335047 (C4 (Web Text))

Max Activating Token Index: 121

Text #10

Max Range: 3.5971. Min Range: -3.5971

Max Act: 2.0214. Min Act: -0.0000

Data Index: 679153 (C4 (Web Text))

Max Activating Token Index: 169

Text #11

Max Range: 3.5971. Min Range: -3.5971

Max Act: 2.0867. Min Act: -0.0000

Data Index: 1347470 (C4 (Web Text))

Max Activating Token Index: 191

Text #12

Max Range: 3.5971. Min Range: -3.5971

Max Act: 2.1365. Min Act: -0.0000

Data Index: 5225 (C4 (Web Text))

Max Activating Token Index: 135

Text #13

Max Range: 3.5971. Min Range: -3.5971

Max Act: 2.1294. Min Act: -0.0000

Data Index: 1165329 (C4 (Web Text))

Max Activating Token Index: 834

Text #14

Max Range: 3.5971. Min Range: -3.5971

Max Act: 1.8741. Min Act: -0.0000

Data Index: 971897 (C4 (Web Text))

Max Activating Token Index: 297

Text #15

Max Range: 3.5971. Min Range: -3.5971

Max Act: 1.9478. Min Act: -0.0000

Data Index: 485064 (C4 (Web Text))

Max Activating Token Index: 294

Text #16

Max Range: 3.5971. Min Range: -3.5971

Max Act: 1.9270. Min Act: -0.0000

Data Index: 687510 (C4 (Web Text))

Max Activating Token Index: 572

Text #17

Max Range: 3.5971. Min Range: -3.5971

Max Act: 1.7630. Min Act: -0.0000

Data Index: 123774 (C4 (Web Text))

Max Activating Token Index: 520

Text #18

Max Range: 3.5971. Min Range: -3.5971

Max Act: 1.8944. Min Act: -0.0000

Data Index: 40682 (C4 (Web Text))

Max Activating Token Index: 594

Text #19

Max Range: 3.5971. Min Range: -3.5971

Max Act: 1.8533. Min Act: -0.0000

Data Index: 1048283 (C4 (Web Text))

Max Activating Token Index: 681