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

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

Neuron 3491 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9255. Min Range: -0.9255

Max Act: 0.9255. Min Act: -0.0000

Data Index: 732504 (C4 (Web Text))

Max Activating Token Index: 887

Text #1

Max Range: 0.9255. Min Range: -0.9255

Max Act: 0.8422. Min Act: -0.0000

Data Index: 1355406 (C4 (Web Text))

Max Activating Token Index: 257

Text #2

Max Range: 0.9255. Min Range: -0.9255

Max Act: 0.8491. Min Act: -0.0000

Data Index: 979121 (C4 (Web Text))

Max Activating Token Index: 1004

Text #3

Max Range: 0.9255. Min Range: -0.9255

Max Act: 0.8078. Min Act: -0.0000

Data Index: 643714 (C4 (Web Text))

Max Activating Token Index: 605

Text #4

Max Range: 0.9255. Min Range: -0.9255

Max Act: 0.7749. Min Act: -0.0001

Data Index: 524729 (C4 (Web Text))

Max Activating Token Index: 228

Text #5

Max Range: 0.9255. Min Range: -0.9255

Max Act: 0.7657. Min Act: -0.0000

Data Index: 327968 (C4 (Web Text))

Max Activating Token Index: 354

Text #6

Max Range: 0.9255. Min Range: -0.9255

Max Act: 0.7600. Min Act: -0.0001

Data Index: 1134259 (C4 (Web Text))

Max Activating Token Index: 110

Text #7

Max Range: 0.9255. Min Range: -0.9255

Max Act: 0.7468. Min Act: -0.0001

Data Index: 721680 (C4 (Web Text))

Max Activating Token Index: 982

Text #8

Max Range: 0.9255. Min Range: -0.9255

Max Act: 0.7344. Min Act: -0.0001

Data Index: 1208408 (C4 (Web Text))

Max Activating Token Index: 829

Text #9

Max Range: 0.9255. Min Range: -0.9255

Max Act: 0.6650. Min Act: -0.0001

Data Index: 1190824 (C4 (Web Text))

Max Activating Token Index: 963

Text #10

Max Range: 0.9255. Min Range: -0.9255

Max Act: 0.7060. Min Act: -0.0000

Data Index: 574026 (C4 (Web Text))

Max Activating Token Index: 945

Text #11

Max Range: 0.9255. Min Range: -0.9255

Max Act: 0.6827. Min Act: -0.0000

Data Index: 877233 (C4 (Web Text))

Max Activating Token Index: 295

Text #12

Max Range: 0.9255. Min Range: -0.9255

Max Act: 0.6820. Min Act: -0.0000

Data Index: 1214420 (C4 (Web Text))

Max Activating Token Index: 110

Text #13

Max Range: 0.9255. Min Range: -0.9255

Max Act: 0.6902. Min Act: -0.0000

Data Index: 167769 (C4 (Web Text))

Max Activating Token Index: 21

Text #14

Max Range: 0.9255. Min Range: -0.9255

Max Act: 0.6531. Min Act: -0.0001

Data Index: 228401 (C4 (Web Text))

Max Activating Token Index: 802

Text #15

Max Range: 0.9255. Min Range: -0.9255

Max Act: 0.6296. Min Act: -0.0001

Data Index: 496487 (C4 (Web Text))

Max Activating Token Index: 735

Text #16

Max Range: 0.9255. Min Range: -0.9255

Max Act: 0.6830. Min Act: -0.0000

Data Index: 791641 (C4 (Web Text))

Max Activating Token Index: 500

Text #17

Max Range: 0.9255. Min Range: -0.9255

Max Act: 0.6951. Min Act: -0.0001

Data Index: 149977 (C4 (Web Text))

Max Activating Token Index: 602

Text #18

Max Range: 0.9255. Min Range: -0.9255

Max Act: 0.6423. Min Act: -0.0001

Data Index: 331435 (C4 (Web Text))

Max Activating Token Index: 393

Text #19

Max Range: 0.9255. Min Range: -0.9255

Max Act: 0.6412. Min Act: -0.0000

Data Index: 297845 (C4 (Web Text))

Max Activating Token Index: 172