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

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

Neuron 4375 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0166. Min Range: -2.0166

Max Act: 1.9092. Min Act: -0.0000

Data Index: 1325972 (C4 (Web Text))

Max Activating Token Index: 860

Text #1

Max Range: 2.0166. Min Range: -2.0166

Max Act: 1.8649. Min Act: -0.0000

Data Index: 5051 (C4 (Web Text))

Max Activating Token Index: 46

Text #2

Max Range: 2.0166. Min Range: -2.0166

Max Act: 2.0166. Min Act: -0.0000

Data Index: 24665 (C4 (Web Text))

Max Activating Token Index: 948

Text #3

Max Range: 2.0166. Min Range: -2.0166

Max Act: 1.7932. Min Act: -0.0000

Data Index: 351273 (C4 (Web Text))

Max Activating Token Index: 307

Text #4

Max Range: 2.0166. Min Range: -2.0166

Max Act: 1.8734. Min Act: -0.0000

Data Index: 610249 (C4 (Web Text))

Max Activating Token Index: 66

Text #5

Max Range: 2.0166. Min Range: -2.0166

Max Act: 1.9107. Min Act: -0.0000

Data Index: 907140 (C4 (Web Text))

Max Activating Token Index: 840

Text #6

Max Range: 2.0166. Min Range: -2.0166

Max Act: 1.5820. Min Act: -0.0000

Data Index: 679087 (C4 (Web Text))

Max Activating Token Index: 136

Text #7

Max Range: 2.0166. Min Range: -2.0166

Max Act: 1.7654. Min Act: -0.0000

Data Index: 1182763 (C4 (Web Text))

Max Activating Token Index: 508

Text #8

Max Range: 2.0166. Min Range: -2.0166

Max Act: 1.5727. Min Act: -0.0000

Data Index: 885963 (C4 (Web Text))

Max Activating Token Index: 835

Text #9

Max Range: 2.0166. Min Range: -2.0166

Max Act: 1.5625. Min Act: -0.0000

Data Index: 44514 (C4 (Web Text))

Max Activating Token Index: 844

Text #10

Max Range: 2.0166. Min Range: -2.0166

Max Act: 1.4856. Min Act: -0.0000

Data Index: 1203353 (C4 (Web Text))

Max Activating Token Index: 955

Text #11

Max Range: 2.0166. Min Range: -2.0166

Max Act: 1.5055. Min Act: -0.0000

Data Index: 883954 (C4 (Web Text))

Max Activating Token Index: 783

Text #12

Max Range: 2.0166. Min Range: -2.0166

Max Act: 1.5067. Min Act: -0.0000

Data Index: 574527 (C4 (Web Text))

Max Activating Token Index: 64

Text #13

Max Range: 2.0166. Min Range: -2.0166

Max Act: 1.4089. Min Act: -0.0000

Data Index: 82605 (C4 (Web Text))

Max Activating Token Index: 869

Text #14

Max Range: 2.0166. Min Range: -2.0166

Max Act: 1.3963. Min Act: -0.0000

Data Index: 27241 (C4 (Web Text))

Max Activating Token Index: 21

Text #15

Max Range: 2.0166. Min Range: -2.0166

Max Act: 1.5511. Min Act: -0.0000

Data Index: 210983 (C4 (Web Text))

Max Activating Token Index: 453

Text #16

Max Range: 2.0166. Min Range: -2.0166

Max Act: 1.3511. Min Act: -0.0000

Data Index: 553489 (C4 (Web Text))

Max Activating Token Index: 42

Text #17

Max Range: 2.0166. Min Range: -2.0166

Max Act: 1.3339. Min Act: -0.0000

Data Index: 732574 (C4 (Web Text))

Max Activating Token Index: 674

Text #18

Max Range: 2.0166. Min Range: -2.0166

Max Act: 1.4032. Min Act: -0.0000

Data Index: 1229298 (C4 (Web Text))

Max Activating Token Index: 507

Text #19

Max Range: 2.0166. Min Range: -2.0166

Max Act: 1.3285. Min Act: -0.0000

Data Index: 400328 (C4 (Web Text))

Max Activating Token Index: 778