Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1688 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.5358. Min Range: -0.5358

Max Act: 0.4503. Min Act: -0.0002

Data Index: 1008282 (C4 (Web Text))

Max Activating Token Index: 916

Text #1

Max Range: 0.5358. Min Range: -0.5358

Max Act: 0.5170. Min Act: -0.0001

Data Index: 234851 (C4 (Web Text))

Max Activating Token Index: 849

Text #2

Max Range: 0.5358. Min Range: -0.5358

Max Act: 0.5156. Min Act: -0.0001

Data Index: 889426 (C4 (Web Text))

Max Activating Token Index: 994

Text #3

Max Range: 0.5358. Min Range: -0.5358

Max Act: 0.4940. Min Act: -0.0001

Data Index: 1023037 (C4 (Web Text))

Max Activating Token Index: 224

Text #4

Max Range: 0.5358. Min Range: -0.5358

Max Act: 0.4687. Min Act: -0.0001

Data Index: 196313 (C4 (Web Text))

Max Activating Token Index: 596

Text #5

Max Range: 0.5358. Min Range: -0.5358

Max Act: 0.5193. Min Act: -0.0001

Data Index: 807542 (C4 (Web Text))

Max Activating Token Index: 375

Text #6

Max Range: 0.5358. Min Range: -0.5358

Max Act: 0.4933. Min Act: -0.0002

Data Index: 1066002 (C4 (Web Text))

Max Activating Token Index: 843

Text #7

Max Range: 0.5358. Min Range: -0.5358

Max Act: 0.4917. Min Act: -0.0002

Data Index: 46060 (C4 (Web Text))

Max Activating Token Index: 167

Text #8

Max Range: 0.5358. Min Range: -0.5358

Max Act: 0.4861. Min Act: -0.0001

Data Index: 25353 (C4 (Web Text))

Max Activating Token Index: 46

Text #9

Max Range: 0.5358. Min Range: -0.5358

Max Act: 0.5358. Min Act: -0.0001

Data Index: 1310381 (C4 (Web Text))

Max Activating Token Index: 922

Text #10

Max Range: 0.5358. Min Range: -0.5358

Max Act: 0.4802. Min Act: -0.0002

Data Index: 1304791 (C4 (Web Text))

Max Activating Token Index: 384

Text #11

Max Range: 0.5358. Min Range: -0.5358

Max Act: 0.4621. Min Act: -0.0001

Data Index: 461770 (C4 (Web Text))

Max Activating Token Index: 1018

Text #12

Max Range: 0.5358. Min Range: -0.5358

Max Act: 0.4754. Min Act: -0.0001

Data Index: 515697 (C4 (Web Text))

Max Activating Token Index: 755

Text #13

Max Range: 0.5358. Min Range: -0.5358

Max Act: 0.4869. Min Act: -0.0001

Data Index: 111944 (C4 (Web Text))

Max Activating Token Index: 104

Text #14

Max Range: 0.5358. Min Range: -0.5358

Max Act: 0.4689. Min Act: -0.0001

Data Index: 708041 (C4 (Web Text))

Max Activating Token Index: 69

Text #15

Max Range: 0.5358. Min Range: -0.5358

Max Act: 0.4138. Min Act: -0.0001

Data Index: 680271 (C4 (Web Text))

Max Activating Token Index: 552

Text #16

Max Range: 0.5358. Min Range: -0.5358

Max Act: 0.4422. Min Act: -0.0002

Data Index: 51852 (C4 (Web Text))

Max Activating Token Index: 855

Text #17

Max Range: 0.5358. Min Range: -0.5358

Max Act: 0.4703. Min Act: -0.0001

Data Index: 911523 (C4 (Web Text))

Max Activating Token Index: 540

Text #18

Max Range: 0.5358. Min Range: -0.5358

Max Act: 0.4372. Min Act: -0.0001

Data Index: 606955 (C4 (Web Text))

Max Activating Token Index: 924

Text #19

Max Range: 0.5358. Min Range: -0.5358

Max Act: 0.4382. Min Act: -0.0001

Data Index: 1201217 (C4 (Web Text))

Max Activating Token Index: 32