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

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

Neuron 2852 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5200. Min Range: -0.5200

Max Act: 0.5200. Min Act: -0.0001

Data Index: 34405 (C4 (Web Text))

Max Activating Token Index: 45

Text #1

Max Range: 0.5200. Min Range: -0.5200

Max Act: 0.4583. Min Act: -0.0001

Data Index: 574464 (C4 (Web Text))

Max Activating Token Index: 565

Text #2

Max Range: 0.5200. Min Range: -0.5200

Max Act: 0.4525. Min Act: -0.0001

Data Index: 1146479 (C4 (Web Text))

Max Activating Token Index: 117

Text #3

Max Range: 0.5200. Min Range: -0.5200

Max Act: 0.4440. Min Act: -0.0001

Data Index: 515921 (C4 (Web Text))

Max Activating Token Index: 956

Text #4

Max Range: 0.5200. Min Range: -0.5200

Max Act: 0.4544. Min Act: -0.0001

Data Index: 1117430 (C4 (Web Text))

Max Activating Token Index: 454

Text #5

Max Range: 0.5200. Min Range: -0.5200

Max Act: 0.4635. Min Act: -0.0001

Data Index: 379218 (C4 (Web Text))

Max Activating Token Index: 397

Text #6

Max Range: 0.5200. Min Range: -0.5200

Max Act: 0.4452. Min Act: -0.0001

Data Index: 774256 (C4 (Web Text))

Max Activating Token Index: 488

Text #7

Max Range: 0.5200. Min Range: -0.5200

Max Act: 0.4229. Min Act: -0.0001

Data Index: 637719 (C4 (Web Text))

Max Activating Token Index: 403

Text #8

Max Range: 0.5200. Min Range: -0.5200

Max Act: 0.4481. Min Act: -0.0001

Data Index: 823239 (C4 (Web Text))

Max Activating Token Index: 588

Text #9

Max Range: 0.5200. Min Range: -0.5200

Max Act: 0.4445. Min Act: -0.0001

Data Index: 198481 (C4 (Web Text))

Max Activating Token Index: 362

Text #10

Max Range: 0.5200. Min Range: -0.5200

Max Act: 0.3895. Min Act: -0.0001

Data Index: 16388 (C4 (Web Text))

Max Activating Token Index: 501

Text #11

Max Range: 0.5200. Min Range: -0.5200

Max Act: 0.4034. Min Act: -0.0001

Data Index: 375108 (C4 (Web Text))

Max Activating Token Index: 926

Text #12

Max Range: 0.5200. Min Range: -0.5200

Max Act: 0.4408. Min Act: -0.0001

Data Index: 168000 (C4 (Web Text))

Max Activating Token Index: 249

Text #13

Max Range: 0.5200. Min Range: -0.5200

Max Act: 0.4258. Min Act: -0.0001

Data Index: 937580 (C4 (Web Text))

Max Activating Token Index: 380

Text #14

Max Range: 0.5200. Min Range: -0.5200

Max Act: 0.4242. Min Act: -0.0001

Data Index: 677698 (C4 (Web Text))

Max Activating Token Index: 424

Text #15

Max Range: 0.5200. Min Range: -0.5200

Max Act: 0.4215. Min Act: -0.0001

Data Index: 920689 (C4 (Web Text))

Max Activating Token Index: 599

Text #16

Max Range: 0.5200. Min Range: -0.5200

Max Act: 0.4004. Min Act: -0.0001

Data Index: 942062 (C4 (Web Text))

Max Activating Token Index: 364

Text #17

Max Range: 0.5200. Min Range: -0.5200

Max Act: 0.4035. Min Act: -0.0001

Data Index: 706932 (C4 (Web Text))

Max Activating Token Index: 284

Text #18

Max Range: 0.5200. Min Range: -0.5200

Max Act: 0.3988. Min Act: -0.0001

Data Index: 88959 (C4 (Web Text))

Max Activating Token Index: 640

Text #19

Max Range: 0.5200. Min Range: -0.5200

Max Act: 0.4100. Min Act: -0.0001

Data Index: 1052234 (C4 (Web Text))

Max Activating Token Index: 246