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

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

Neuron 883 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: 1.5845. Min Range: -1.5845

Max Act: 1.5845. Min Act: -0.0000

Data Index: 620497 (C4 (Web Text))

Max Activating Token Index: 290

Text #1

Max Range: 1.5845. Min Range: -1.5845

Max Act: 1.4863. Min Act: -0.0000

Data Index: 153804 (C4 (Web Text))

Max Activating Token Index: 111

Text #2

Max Range: 1.5845. Min Range: -1.5845

Max Act: 1.5250. Min Act: -0.0000

Data Index: 903532 (C4 (Web Text))

Max Activating Token Index: 285

Text #3

Max Range: 1.5845. Min Range: -1.5845

Max Act: 1.4389. Min Act: 0.0000

Data Index: 3216 (C4 (Web Text))

Max Activating Token Index: 107

Text #4

Max Range: 1.5845. Min Range: -1.5845

Max Act: 1.3941. Min Act: -0.0000

Data Index: 861751 (C4 (Web Text))

Max Activating Token Index: 345

Text #5

Max Range: 1.5845. Min Range: -1.5845

Max Act: 1.3605. Min Act: -0.0000

Data Index: 1177159 (C4 (Web Text))

Max Activating Token Index: 90

Text #6

Max Range: 1.5845. Min Range: -1.5845

Max Act: 1.4541. Min Act: -0.0000

Data Index: 514745 (C4 (Web Text))

Max Activating Token Index: 372

Text #7

Max Range: 1.5845. Min Range: -1.5845

Max Act: 1.2600. Min Act: -0.0000

Data Index: 615994 (C4 (Web Text))

Max Activating Token Index: 146

Text #8

Max Range: 1.5845. Min Range: -1.5845

Max Act: 1.3014. Min Act: -0.0000

Data Index: 204045 (C4 (Web Text))

Max Activating Token Index: 505

Text #9

Max Range: 1.5845. Min Range: -1.5845

Max Act: 1.1989. Min Act: -0.0000

Data Index: 777545 (C4 (Web Text))

Max Activating Token Index: 115

Text #10

Max Range: 1.5845. Min Range: -1.5845

Max Act: 1.2943. Min Act: 0.0000

Data Index: 67270 (C4 (Web Text))

Max Activating Token Index: 488

Text #11

Max Range: 1.5845. Min Range: -1.5845

Max Act: 1.2001. Min Act: -0.0000

Data Index: 655985 (C4 (Web Text))

Max Activating Token Index: 39

Text #12

Max Range: 1.5845. Min Range: -1.5845

Max Act: 1.1975. Min Act: -0.0000

Data Index: 1093181 (C4 (Web Text))

Max Activating Token Index: 796

Text #13

Max Range: 1.5845. Min Range: -1.5845

Max Act: 1.1297. Min Act: -0.0000

Data Index: 107124 (C4 (Web Text))

Max Activating Token Index: 886

Text #14

Max Range: 1.5845. Min Range: -1.5845

Max Act: 1.1874. Min Act: -0.0000

Data Index: 1346881 (C4 (Web Text))

Max Activating Token Index: 1014

Text #15

Max Range: 1.5845. Min Range: -1.5845

Max Act: 1.1691. Min Act: -0.0000

Data Index: 790809 (C4 (Web Text))

Max Activating Token Index: 53

Text #16

Max Range: 1.5845. Min Range: -1.5845

Max Act: 1.1813. Min Act: 0.0000

Data Index: 1096608 (C4 (Web Text))

Max Activating Token Index: 338

Text #17

Max Range: 1.5845. Min Range: -1.5845

Max Act: 1.1727. Min Act: -0.0000

Data Index: 355936 (C4 (Web Text))

Max Activating Token Index: 541

Text #18

Max Range: 1.5845. Min Range: -1.5845

Max Act: 1.1665. Min Act: 0.0000

Data Index: 1294535 (C4 (Web Text))

Max Activating Token Index: 112

Text #19

Max Range: 1.5845. Min Range: -1.5845

Max Act: 1.1601. Min Act: -0.0000

Data Index: 123700 (C4 (Web Text))

Max Activating Token Index: 150