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

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

Neuron 1651 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: 1.7159. Min Range: -1.7159

Max Act: 1.7159. Min Act: -0.0000

Data Index: 691756 (C4 (Web Text))

Max Activating Token Index: 988

Text #1

Max Range: 1.7159. Min Range: -1.7159

Max Act: 1.7114. Min Act: -0.0000

Data Index: 578397 (C4 (Web Text))

Max Activating Token Index: 546

Text #2

Max Range: 1.7159. Min Range: -1.7159

Max Act: 1.6791. Min Act: -0.0000

Data Index: 335146 (C4 (Web Text))

Max Activating Token Index: 424

Text #3

Max Range: 1.7159. Min Range: -1.7159

Max Act: 1.5391. Min Act: -0.0000

Data Index: 1324166 (C4 (Web Text))

Max Activating Token Index: 218

Text #4

Max Range: 1.7159. Min Range: -1.7159

Max Act: 1.4300. Min Act: -0.0000

Data Index: 956893 (C4 (Web Text))

Max Activating Token Index: 697

Text #5

Max Range: 1.7159. Min Range: -1.7159

Max Act: 1.4125. Min Act: -0.0000

Data Index: 1257567 (C4 (Web Text))

Max Activating Token Index: 30

Text #6

Max Range: 1.7159. Min Range: -1.7159

Max Act: 1.3596. Min Act: -0.0000

Data Index: 935713 (C4 (Web Text))

Max Activating Token Index: 490

Text #7

Max Range: 1.7159. Min Range: -1.7159

Max Act: 1.3407. Min Act: -0.0000

Data Index: 54671 (C4 (Web Text))

Max Activating Token Index: 115

Text #8

Max Range: 1.7159. Min Range: -1.7159

Max Act: 1.3402. Min Act: -0.0000

Data Index: 227387 (C4 (Web Text))

Max Activating Token Index: 447

Text #9

Max Range: 1.7159. Min Range: -1.7159

Max Act: 1.3259. Min Act: -0.0000

Data Index: 588803 (C4 (Web Text))

Max Activating Token Index: 278

Text #10

Max Range: 1.7159. Min Range: -1.7159

Max Act: 1.2671. Min Act: -0.0000

Data Index: 1228240 (C4 (Web Text))

Max Activating Token Index: 444

Text #11

Max Range: 1.7159. Min Range: -1.7159

Max Act: 1.3060. Min Act: -0.0000

Data Index: 1584663 (Python Code)

Max Activating Token Index: 377

Text #12

Max Range: 1.7159. Min Range: -1.7159

Max Act: 1.3203. Min Act: 0.0000

Data Index: 891749 (C4 (Web Text))

Max Activating Token Index: 933

Text #13

Max Range: 1.7159. Min Range: -1.7159

Max Act: 1.2962. Min Act: 0.0000

Data Index: 156022 (C4 (Web Text))

Max Activating Token Index: 587

Text #14

Max Range: 1.7159. Min Range: -1.7159

Max Act: 1.2138. Min Act: -0.0000

Data Index: 653349 (C4 (Web Text))

Max Activating Token Index: 797

Text #15

Max Range: 1.7159. Min Range: -1.7159

Max Act: 1.1728. Min Act: -0.0000

Data Index: 1355619 (C4 (Web Text))

Max Activating Token Index: 361

Text #16

Max Range: 1.7159. Min Range: -1.7159

Max Act: 1.2382. Min Act: -0.0000

Data Index: 1056872 (C4 (Web Text))

Max Activating Token Index: 559

Text #17

Max Range: 1.7159. Min Range: -1.7159

Max Act: 1.2010. Min Act: -0.0000

Data Index: 1503806 (Python Code)

Max Activating Token Index: 733

Text #18

Max Range: 1.7159. Min Range: -1.7159

Max Act: 1.1561. Min Act: -0.0000

Data Index: 200861 (C4 (Web Text))

Max Activating Token Index: 450

Text #19

Max Range: 1.7159. Min Range: -1.7159

Max Act: 1.1088. Min Act: -0.0000

Data Index: 192526 (C4 (Web Text))

Max Activating Token Index: 268