Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4528 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.4563. Min Range: -1.4563

Max Act: 1.3172. Min Act: -0.0000

Data Index: 488767 (C4 (Web Text))

Max Activating Token Index: 224

Text #1

Max Range: 1.4563. Min Range: -1.4563

Max Act: 1.4563. Min Act: -0.0000

Data Index: 1253708 (C4 (Web Text))

Max Activating Token Index: 669

Text #2

Max Range: 1.4563. Min Range: -1.4563

Max Act: 1.2294. Min Act: -0.0000

Data Index: 1316137 (C4 (Web Text))

Max Activating Token Index: 380

Text #3

Max Range: 1.4563. Min Range: -1.4563

Max Act: 1.0704. Min Act: -0.0000

Data Index: 1061515 (C4 (Web Text))

Max Activating Token Index: 465

Text #4

Max Range: 1.4563. Min Range: -1.4563

Max Act: 1.0669. Min Act: -0.0000

Data Index: 593721 (C4 (Web Text))

Max Activating Token Index: 894

Text #5

Max Range: 1.4563. Min Range: -1.4563

Max Act: 0.9798. Min Act: -0.0000

Data Index: 201627 (C4 (Web Text))

Max Activating Token Index: 113

Text #6

Max Range: 1.4563. Min Range: -1.4563

Max Act: 1.0315. Min Act: -0.0000

Data Index: 293058 (C4 (Web Text))

Max Activating Token Index: 484

Text #7

Max Range: 1.4563. Min Range: -1.4563

Max Act: 1.0309. Min Act: -0.0000

Data Index: 1032171 (C4 (Web Text))

Max Activating Token Index: 492

Text #8

Max Range: 1.4563. Min Range: -1.4563

Max Act: 1.0165. Min Act: -0.0000

Data Index: 1154421 (C4 (Web Text))

Max Activating Token Index: 998

Text #9

Max Range: 1.4563. Min Range: -1.4563

Max Act: 1.0165. Min Act: 0.0000

Data Index: 901199 (C4 (Web Text))

Max Activating Token Index: 144

Text #10

Max Range: 1.4563. Min Range: -1.4563

Max Act: 1.2105. Min Act: -0.0000

Data Index: 781759 (C4 (Web Text))

Max Activating Token Index: 667

Text #11

Max Range: 1.4563. Min Range: -1.4563

Max Act: 1.0027. Min Act: -0.0000

Data Index: 678692 (C4 (Web Text))

Max Activating Token Index: 333

Text #12

Max Range: 1.4563. Min Range: -1.4563

Max Act: 0.9628. Min Act: -0.0000

Data Index: 1274862 (C4 (Web Text))

Max Activating Token Index: 266

Text #13

Max Range: 1.4563. Min Range: -1.4563

Max Act: 0.8992. Min Act: -0.0000

Data Index: 504941 (C4 (Web Text))

Max Activating Token Index: 727

Text #14

Max Range: 1.4563. Min Range: -1.4563

Max Act: 0.9509. Min Act: -0.0000

Data Index: 955435 (C4 (Web Text))

Max Activating Token Index: 466

Text #15

Max Range: 1.4563. Min Range: -1.4563

Max Act: 0.9291. Min Act: -0.0000

Data Index: 457620 (C4 (Web Text))

Max Activating Token Index: 866

Text #16

Max Range: 1.4563. Min Range: -1.4563

Max Act: 0.9178. Min Act: -0.0000

Data Index: 9279 (C4 (Web Text))

Max Activating Token Index: 432

Text #17

Max Range: 1.4563. Min Range: -1.4563

Max Act: 0.8673. Min Act: -0.0000

Data Index: 996588 (C4 (Web Text))

Max Activating Token Index: 355

Text #18

Max Range: 1.4563. Min Range: -1.4563

Max Act: 0.9750. Min Act: -0.0000

Data Index: 382593 (C4 (Web Text))

Max Activating Token Index: 503

Text #19

Max Range: 1.4563. Min Range: -1.4563

Max Act: 0.9089. Min Act: -0.0000

Data Index: 172613 (C4 (Web Text))

Max Activating Token Index: 93