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

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

Neuron 1980 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: 1.2563. Min Range: -1.2563

Max Act: 1.2563. Min Act: -0.0000

Data Index: 227432 (C4 (Web Text))

Max Activating Token Index: 969

Text #1

Max Range: 1.2563. Min Range: -1.2563

Max Act: 1.2337. Min Act: -0.0000

Data Index: 130039 (C4 (Web Text))

Max Activating Token Index: 519

Text #2

Max Range: 1.2563. Min Range: -1.2563

Max Act: 0.6260. Min Act: -0.0000

Data Index: 140954 (C4 (Web Text))

Max Activating Token Index: 356

Text #3

Max Range: 1.2563. Min Range: -1.2563

Max Act: 0.6698. Min Act: -0.0000

Data Index: 696923 (C4 (Web Text))

Max Activating Token Index: 269

Text #4

Max Range: 1.2563. Min Range: -1.2563

Max Act: 0.6581. Min Act: -0.0000

Data Index: 761839 (C4 (Web Text))

Max Activating Token Index: 159

Text #5

Max Range: 1.2563. Min Range: -1.2563

Max Act: 0.6273. Min Act: -0.0000

Data Index: 1635094 (Python Code)

Max Activating Token Index: 654

Text #6

Max Range: 1.2563. Min Range: -1.2563

Max Act: 0.5913. Min Act: -0.0000

Data Index: 1282085 (C4 (Web Text))

Max Activating Token Index: 55

Text #7

Max Range: 1.2563. Min Range: -1.2563

Max Act: 0.5175. Min Act: -0.0000

Data Index: 238162 (C4 (Web Text))

Max Activating Token Index: 749

Text #8

Max Range: 1.2563. Min Range: -1.2563

Max Act: 0.5309. Min Act: -0.0000

Data Index: 22614 (C4 (Web Text))

Max Activating Token Index: 754

Text #9

Max Range: 1.2563. Min Range: -1.2563

Max Act: 0.4926. Min Act: -0.0000

Data Index: 677471 (C4 (Web Text))

Max Activating Token Index: 190

Text #10

Max Range: 1.2563. Min Range: -1.2563

Max Act: 0.5194. Min Act: -0.0000

Data Index: 684347 (C4 (Web Text))

Max Activating Token Index: 677

Text #11

Max Range: 1.2563. Min Range: -1.2563

Max Act: 0.5172. Min Act: -0.0000

Data Index: 992831 (C4 (Web Text))

Max Activating Token Index: 686

Text #12

Max Range: 1.2563. Min Range: -1.2563

Max Act: 0.5059. Min Act: -0.0000

Data Index: 417068 (C4 (Web Text))

Max Activating Token Index: 512

Text #13

Max Range: 1.2563. Min Range: -1.2563

Max Act: 0.5086. Min Act: 0.0000

Data Index: 570999 (C4 (Web Text))

Max Activating Token Index: 782

Text #14

Max Range: 1.2563. Min Range: -1.2563

Max Act: 0.5560. Min Act: -0.0000

Data Index: 506168 (C4 (Web Text))

Max Activating Token Index: 817

Text #15

Max Range: 1.2563. Min Range: -1.2563

Max Act: 0.4888. Min Act: -0.0000

Data Index: 1103647 (C4 (Web Text))

Max Activating Token Index: 1014

Text #16

Max Range: 1.2563. Min Range: -1.2563

Max Act: 0.4885. Min Act: -0.0000

Data Index: 22691 (C4 (Web Text))

Max Activating Token Index: 265

Text #17

Max Range: 1.2563. Min Range: -1.2563

Max Act: 0.4857. Min Act: -0.0000

Data Index: 754671 (C4 (Web Text))

Max Activating Token Index: 822

Text #18

Max Range: 1.2563. Min Range: -1.2563

Max Act: 0.4910. Min Act: -0.0000

Data Index: 788641 (C4 (Web Text))

Max Activating Token Index: 882

Text #19

Max Range: 1.2563. Min Range: -1.2563

Max Act: 0.4707. Min Act: -0.0000

Data Index: 265554 (C4 (Web Text))

Max Activating Token Index: 658