Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3971 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.9763. Min Range: -0.9763

Max Act: 0.9763. Min Act: -0.0000

Data Index: 1557086 (Python Code)

Max Activating Token Index: 28

Text #1

Max Range: 0.9763. Min Range: -0.9763

Max Act: 0.9105. Min Act: -0.0000

Data Index: 1485896 (Python Code)

Max Activating Token Index: 836

Text #2

Max Range: 0.9763. Min Range: -0.9763

Max Act: 0.8942. Min Act: -0.0000

Data Index: 157969 (C4 (Web Text))

Max Activating Token Index: 410

Text #3

Max Range: 0.9763. Min Range: -0.9763

Max Act: 0.8580. Min Act: -0.0000

Data Index: 1450410 (Python Code)

Max Activating Token Index: 436

Text #4

Max Range: 0.9763. Min Range: -0.9763

Max Act: 0.9148. Min Act: -0.0000

Data Index: 714509 (C4 (Web Text))

Max Activating Token Index: 986

Text #5

Max Range: 0.9763. Min Range: -0.9763

Max Act: 0.7759. Min Act: -0.0000

Data Index: 798420 (C4 (Web Text))

Max Activating Token Index: 560

Text #6

Max Range: 0.9763. Min Range: -0.9763

Max Act: 0.7692. Min Act: -0.0000

Data Index: 534621 (C4 (Web Text))

Max Activating Token Index: 796

Text #7

Max Range: 0.9763. Min Range: -0.9763

Max Act: 0.7471. Min Act: -0.0000

Data Index: 718673 (C4 (Web Text))

Max Activating Token Index: 266

Text #8

Max Range: 0.9763. Min Range: -0.9763

Max Act: 0.7975. Min Act: -0.0000

Data Index: 261159 (C4 (Web Text))

Max Activating Token Index: 648

Text #9

Max Range: 0.9763. Min Range: -0.9763

Max Act: 0.7334. Min Act: -0.0000

Data Index: 353781 (C4 (Web Text))

Max Activating Token Index: 287

Text #10

Max Range: 0.9763. Min Range: -0.9763

Max Act: 0.7348. Min Act: -0.0000

Data Index: 883568 (C4 (Web Text))

Max Activating Token Index: 743

Text #11

Max Range: 0.9763. Min Range: -0.9763

Max Act: 0.7346. Min Act: -0.0000

Data Index: 425453 (C4 (Web Text))

Max Activating Token Index: 355

Text #12

Max Range: 0.9763. Min Range: -0.9763

Max Act: 0.7252. Min Act: -0.0000

Data Index: 1344488 (C4 (Web Text))

Max Activating Token Index: 715

Text #13

Max Range: 0.9763. Min Range: -0.9763

Max Act: 0.6898. Min Act: 0.0000

Data Index: 178788 (C4 (Web Text))

Max Activating Token Index: 760

Text #14

Max Range: 0.9763. Min Range: -0.9763

Max Act: 0.6924. Min Act: -0.0000

Data Index: 673321 (C4 (Web Text))

Max Activating Token Index: 721

Text #15

Max Range: 0.9763. Min Range: -0.9763

Max Act: 0.7175. Min Act: -0.0000

Data Index: 123886 (C4 (Web Text))

Max Activating Token Index: 46

Text #16

Max Range: 0.9763. Min Range: -0.9763

Max Act: 0.7079. Min Act: -0.0000

Data Index: 1119151 (C4 (Web Text))

Max Activating Token Index: 513

Text #17

Max Range: 0.9763. Min Range: -0.9763

Max Act: 0.6934. Min Act: -0.0000

Data Index: 899612 (C4 (Web Text))

Max Activating Token Index: 708

Text #18

Max Range: 0.9763. Min Range: -0.9763

Max Act: 0.6462. Min Act: -0.0000

Data Index: 1327535 (C4 (Web Text))

Max Activating Token Index: 725

Text #19

Max Range: 0.9763. Min Range: -0.9763

Max Act: 0.6800. Min Act: -0.0000

Data Index: 374419 (C4 (Web Text))

Max Activating Token Index: 743