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

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

Neuron 4994 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5906. Min Range: -1.5906

Max Act: 1.5906. Min Act: -0.0001

Data Index: 789539 (C4 (Web Text))

Max Activating Token Index: 28

Text #1

Max Range: 1.5906. Min Range: -1.5906

Max Act: 1.4822. Min Act: -0.0001

Data Index: 1262421 (C4 (Web Text))

Max Activating Token Index: 546

Text #2

Max Range: 1.5906. Min Range: -1.5906

Max Act: 1.3475. Min Act: -0.0001

Data Index: 327542 (C4 (Web Text))

Max Activating Token Index: 388

Text #3

Max Range: 1.5906. Min Range: -1.5906

Max Act: 1.3540. Min Act: -0.0001

Data Index: 289019 (C4 (Web Text))

Max Activating Token Index: 93

Text #4

Max Range: 1.5906. Min Range: -1.5906

Max Act: 1.3915. Min Act: -0.0001

Data Index: 52447 (C4 (Web Text))

Max Activating Token Index: 59

Text #5

Max Range: 1.5906. Min Range: -1.5906

Max Act: 1.3716. Min Act: -0.0001

Data Index: 1151463 (C4 (Web Text))

Max Activating Token Index: 484

Text #6

Max Range: 1.5906. Min Range: -1.5906

Max Act: 1.2532. Min Act: -0.0001

Data Index: 663590 (C4 (Web Text))

Max Activating Token Index: 565

Text #7

Max Range: 1.5906. Min Range: -1.5906

Max Act: 1.3745. Min Act: -0.0001

Data Index: 238902 (C4 (Web Text))

Max Activating Token Index: 399

Text #8

Max Range: 1.5906. Min Range: -1.5906

Max Act: 1.3277. Min Act: -0.0001

Data Index: 1203638 (C4 (Web Text))

Max Activating Token Index: 572

Text #9

Max Range: 1.5906. Min Range: -1.5906

Max Act: 1.2813. Min Act: -0.0001

Data Index: 742492 (C4 (Web Text))

Max Activating Token Index: 136

Text #10

Max Range: 1.5906. Min Range: -1.5906

Max Act: 1.2338. Min Act: -0.0001

Data Index: 1071412 (C4 (Web Text))

Max Activating Token Index: 268

Text #11

Max Range: 1.5906. Min Range: -1.5906

Max Act: 1.2347. Min Act: -0.0001

Data Index: 675269 (C4 (Web Text))

Max Activating Token Index: 78

Text #12

Max Range: 1.5906. Min Range: -1.5906

Max Act: 1.2139. Min Act: -0.0001

Data Index: 280118 (C4 (Web Text))

Max Activating Token Index: 46

Text #13

Max Range: 1.5906. Min Range: -1.5906

Max Act: 1.1769. Min Act: -0.0001

Data Index: 1057969 (C4 (Web Text))

Max Activating Token Index: 577

Text #14

Max Range: 1.5906. Min Range: -1.5906

Max Act: 1.1418. Min Act: -0.0001

Data Index: 810161 (C4 (Web Text))

Max Activating Token Index: 700

Text #15

Max Range: 1.5906. Min Range: -1.5906

Max Act: 1.1266. Min Act: -0.0001

Data Index: 296669 (C4 (Web Text))

Max Activating Token Index: 444

Text #16

Max Range: 1.5906. Min Range: -1.5906

Max Act: 1.1864. Min Act: -0.0001

Data Index: 641100 (C4 (Web Text))

Max Activating Token Index: 93

Text #17

Max Range: 1.5906. Min Range: -1.5906

Max Act: 1.2117. Min Act: -0.0001

Data Index: 942609 (C4 (Web Text))

Max Activating Token Index: 210

Text #18

Max Range: 1.5906. Min Range: -1.5906

Max Act: 1.2134. Min Act: -0.0001

Data Index: 1313710 (C4 (Web Text))

Max Activating Token Index: 20

Text #19

Max Range: 1.5906. Min Range: -1.5906

Max Act: 1.1198. Min Act: -0.0001

Data Index: 10887 (C4 (Web Text))

Max Activating Token Index: 348