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

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

Neuron 129 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: 1.7529. Min Range: -1.7529

Max Act: 1.7529. Min Act: -0.0002

Data Index: 1275131 (C4 (Web Text))

Max Activating Token Index: 352

Text #1

Max Range: 1.7529. Min Range: -1.7529

Max Act: 1.1582. Min Act: -0.0002

Data Index: 1252375 (C4 (Web Text))

Max Activating Token Index: 966

Text #2

Max Range: 1.7529. Min Range: -1.7529

Max Act: 1.2689. Min Act: -0.0002

Data Index: 969518 (C4 (Web Text))

Max Activating Token Index: 964

Text #3

Max Range: 1.7529. Min Range: -1.7529

Max Act: 1.0352. Min Act: -0.0002

Data Index: 379058 (C4 (Web Text))

Max Activating Token Index: 355

Text #4

Max Range: 1.7529. Min Range: -1.7529

Max Act: 1.0594. Min Act: -0.0002

Data Index: 808710 (C4 (Web Text))

Max Activating Token Index: 139

Text #5

Max Range: 1.7529. Min Range: -1.7529

Max Act: 1.0702. Min Act: -0.0002

Data Index: 883897 (C4 (Web Text))

Max Activating Token Index: 716

Text #6

Max Range: 1.7529. Min Range: -1.7529

Max Act: 0.9436. Min Act: -0.0002

Data Index: 527382 (C4 (Web Text))

Max Activating Token Index: 495

Text #7

Max Range: 1.7529. Min Range: -1.7529

Max Act: 1.0363. Min Act: -0.0002

Data Index: 1064289 (C4 (Web Text))

Max Activating Token Index: 794

Text #8

Max Range: 1.7529. Min Range: -1.7529

Max Act: 1.0231. Min Act: -0.0002

Data Index: 374656 (C4 (Web Text))

Max Activating Token Index: 840

Text #9

Max Range: 1.7529. Min Range: -1.7529

Max Act: 1.0280. Min Act: -0.0002

Data Index: 355292 (C4 (Web Text))

Max Activating Token Index: 997

Text #10

Max Range: 1.7529. Min Range: -1.7529

Max Act: 1.0782. Min Act: -0.0002

Data Index: 863729 (C4 (Web Text))

Max Activating Token Index: 557

Text #11

Max Range: 1.7529. Min Range: -1.7529

Max Act: 0.8798. Min Act: -0.0001

Data Index: 17612 (C4 (Web Text))

Max Activating Token Index: 984

Text #12

Max Range: 1.7529. Min Range: -1.7529

Max Act: 0.9017. Min Act: -0.0002

Data Index: 587180 (C4 (Web Text))

Max Activating Token Index: 572

Text #13

Max Range: 1.7529. Min Range: -1.7529

Max Act: 0.8080. Min Act: -0.0002

Data Index: 894659 (C4 (Web Text))

Max Activating Token Index: 636

Text #14

Max Range: 1.7529. Min Range: -1.7529

Max Act: 0.9826. Min Act: -0.0002

Data Index: 1198698 (C4 (Web Text))

Max Activating Token Index: 911

Text #15

Max Range: 1.7529. Min Range: -1.7529

Max Act: 0.9791. Min Act: -0.0002

Data Index: 411947 (C4 (Web Text))

Max Activating Token Index: 361

Text #16

Max Range: 1.7529. Min Range: -1.7529

Max Act: 0.8860. Min Act: -0.0002

Data Index: 523949 (C4 (Web Text))

Max Activating Token Index: 959

Text #17

Max Range: 1.7529. Min Range: -1.7529

Max Act: 0.8344. Min Act: -0.0002

Data Index: 475071 (C4 (Web Text))

Max Activating Token Index: 922

Text #18

Max Range: 1.7529. Min Range: -1.7529

Max Act: 0.9329. Min Act: -0.0002

Data Index: 90913 (C4 (Web Text))

Max Activating Token Index: 799

Text #19

Max Range: 1.7529. Min Range: -1.7529

Max Act: 0.9905. Min Act: -0.0002

Data Index: 378226 (C4 (Web Text))

Max Activating Token Index: 482