Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1649 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.7060. Min Range: -0.7060

Max Act: 0.7060. Min Act: -0.0002

Data Index: 1183550 (C4 (Web Text))

Max Activating Token Index: 104

Text #1

Max Range: 0.7060. Min Range: -0.7060

Max Act: 0.6368. Min Act: -0.0002

Data Index: 1211990 (C4 (Web Text))

Max Activating Token Index: 74

Text #2

Max Range: 0.7060. Min Range: -0.7060

Max Act: 0.5022. Min Act: -0.0002

Data Index: 325172 (C4 (Web Text))

Max Activating Token Index: 619

Text #3

Max Range: 0.7060. Min Range: -0.7060

Max Act: 0.6429. Min Act: -0.0002

Data Index: 43958 (C4 (Web Text))

Max Activating Token Index: 48

Text #4

Max Range: 0.7060. Min Range: -0.7060

Max Act: 0.5606. Min Act: -0.0002

Data Index: 673022 (C4 (Web Text))

Max Activating Token Index: 22

Text #5

Max Range: 0.7060. Min Range: -0.7060

Max Act: 0.5947. Min Act: -0.0002

Data Index: 503459 (C4 (Web Text))

Max Activating Token Index: 218

Text #6

Max Range: 0.7060. Min Range: -0.7060

Max Act: 0.5238. Min Act: -0.0002

Data Index: 945607 (C4 (Web Text))

Max Activating Token Index: 962

Text #7

Max Range: 0.7060. Min Range: -0.7060

Max Act: 0.5287. Min Act: -0.0003

Data Index: 687858 (C4 (Web Text))

Max Activating Token Index: 405

Text #8

Max Range: 0.7060. Min Range: -0.7060

Max Act: 0.5086. Min Act: -0.0002

Data Index: 945813 (C4 (Web Text))

Max Activating Token Index: 535

Text #9

Max Range: 0.7060. Min Range: -0.7060

Max Act: 0.5261. Min Act: -0.0002

Data Index: 1156854 (C4 (Web Text))

Max Activating Token Index: 642

Text #10

Max Range: 0.7060. Min Range: -0.7060

Max Act: 0.5931. Min Act: -0.0002

Data Index: 719858 (C4 (Web Text))

Max Activating Token Index: 19

Text #11

Max Range: 0.7060. Min Range: -0.7060

Max Act: 0.5833. Min Act: -0.0002

Data Index: 414272 (C4 (Web Text))

Max Activating Token Index: 580

Text #12

Max Range: 0.7060. Min Range: -0.7060

Max Act: 0.5499. Min Act: -0.0002

Data Index: 655959 (C4 (Web Text))

Max Activating Token Index: 30

Text #13

Max Range: 0.7060. Min Range: -0.7060

Max Act: 0.5586. Min Act: -0.0002

Data Index: 407509 (C4 (Web Text))

Max Activating Token Index: 901

Text #14

Max Range: 0.7060. Min Range: -0.7060

Max Act: 0.5225. Min Act: -0.0002

Data Index: 594730 (C4 (Web Text))

Max Activating Token Index: 400

Text #15

Max Range: 0.7060. Min Range: -0.7060

Max Act: 0.5256. Min Act: -0.0002

Data Index: 921362 (C4 (Web Text))

Max Activating Token Index: 23

Text #16

Max Range: 0.7060. Min Range: -0.7060

Max Act: 0.4879. Min Act: -0.0002

Data Index: 1140475 (C4 (Web Text))

Max Activating Token Index: 517

Text #17

Max Range: 0.7060. Min Range: -0.7060

Max Act: 0.4992. Min Act: -0.0002

Data Index: 146992 (C4 (Web Text))

Max Activating Token Index: 131

Text #18

Max Range: 0.7060. Min Range: -0.7060

Max Act: 0.4458. Min Act: -0.0002

Data Index: 751737 (C4 (Web Text))

Max Activating Token Index: 230

Text #19

Max Range: 0.7060. Min Range: -0.7060

Max Act: 0.4840. Min Act: -0.0002

Data Index: 1144462 (C4 (Web Text))

Max Activating Token Index: 711