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

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

Neuron 3514 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: 0.6352. Min Range: -0.6352

Max Act: 0.6352. Min Act: -0.0002

Data Index: 1301623 (C4 (Web Text))

Max Activating Token Index: 264

Text #1

Max Range: 0.6352. Min Range: -0.6352

Max Act: 0.5384. Min Act: -0.0002

Data Index: 1200474 (C4 (Web Text))

Max Activating Token Index: 192

Text #2

Max Range: 0.6352. Min Range: -0.6352

Max Act: 0.5854. Min Act: -0.0002

Data Index: 1263687 (C4 (Web Text))

Max Activating Token Index: 876

Text #3

Max Range: 0.6352. Min Range: -0.6352

Max Act: 0.5558. Min Act: -0.0002

Data Index: 697925 (C4 (Web Text))

Max Activating Token Index: 741

Text #4

Max Range: 0.6352. Min Range: -0.6352

Max Act: 0.5278. Min Act: -0.0002

Data Index: 554721 (C4 (Web Text))

Max Activating Token Index: 887

Text #5

Max Range: 0.6352. Min Range: -0.6352

Max Act: 0.5089. Min Act: -0.0002

Data Index: 103497 (C4 (Web Text))

Max Activating Token Index: 256

Text #6

Max Range: 0.6352. Min Range: -0.6352

Max Act: 0.5119. Min Act: -0.0002

Data Index: 797979 (C4 (Web Text))

Max Activating Token Index: 431

Text #7

Max Range: 0.6352. Min Range: -0.6352

Max Act: 0.4955. Min Act: -0.0002

Data Index: 23701 (C4 (Web Text))

Max Activating Token Index: 168

Text #8

Max Range: 0.6352. Min Range: -0.6352

Max Act: 0.5357. Min Act: -0.0002

Data Index: 637433 (C4 (Web Text))

Max Activating Token Index: 661

Text #9

Max Range: 0.6352. Min Range: -0.6352

Max Act: 0.5054. Min Act: -0.0002

Data Index: 1104662 (C4 (Web Text))

Max Activating Token Index: 212

Text #10

Max Range: 0.6352. Min Range: -0.6352

Max Act: 0.4929. Min Act: -0.0002

Data Index: 841289 (C4 (Web Text))

Max Activating Token Index: 555

Text #11

Max Range: 0.6352. Min Range: -0.6352

Max Act: 0.4999. Min Act: -0.0002

Data Index: 1317691 (C4 (Web Text))

Max Activating Token Index: 214

Text #12

Max Range: 0.6352. Min Range: -0.6352

Max Act: 0.4783. Min Act: -0.0002

Data Index: 77877 (C4 (Web Text))

Max Activating Token Index: 543

Text #13

Max Range: 0.6352. Min Range: -0.6352

Max Act: 0.5054. Min Act: -0.0002

Data Index: 1145602 (C4 (Web Text))

Max Activating Token Index: 59

Text #14

Max Range: 0.6352. Min Range: -0.6352

Max Act: 0.4993. Min Act: -0.0002

Data Index: 142331 (C4 (Web Text))

Max Activating Token Index: 782

Text #15

Max Range: 0.6352. Min Range: -0.6352

Max Act: 0.4727. Min Act: -0.0002

Data Index: 55726 (C4 (Web Text))

Max Activating Token Index: 983

Text #16

Max Range: 0.6352. Min Range: -0.6352

Max Act: 0.4937. Min Act: -0.0002

Data Index: 705782 (C4 (Web Text))

Max Activating Token Index: 816

Text #17

Max Range: 0.6352. Min Range: -0.6352

Max Act: 0.5304. Min Act: -0.0002

Data Index: 1310640 (C4 (Web Text))

Max Activating Token Index: 599

Text #18

Max Range: 0.6352. Min Range: -0.6352

Max Act: 0.4604. Min Act: -0.0002

Data Index: 732944 (C4 (Web Text))

Max Activating Token Index: 904

Text #19

Max Range: 0.6352. Min Range: -0.6352

Max Act: 0.4249. Min Act: -0.0002

Data Index: 1049619 (C4 (Web Text))

Max Activating Token Index: 168