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

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

Neuron 4523 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8249. Min Range: -0.8249

Max Act: 0.8249. Min Act: -0.0000

Data Index: 823739 (C4 (Web Text))

Max Activating Token Index: 967

Text #1

Max Range: 0.8249. Min Range: -0.8249

Max Act: 0.8144. Min Act: -0.0000

Data Index: 1145709 (C4 (Web Text))

Max Activating Token Index: 648

Text #2

Max Range: 0.8249. Min Range: -0.8249

Max Act: 0.6848. Min Act: -0.0000

Data Index: 440221 (C4 (Web Text))

Max Activating Token Index: 474

Text #3

Max Range: 0.8249. Min Range: -0.8249

Max Act: 0.6319. Min Act: -0.0000

Data Index: 471501 (C4 (Web Text))

Max Activating Token Index: 714

Text #4

Max Range: 0.8249. Min Range: -0.8249

Max Act: 0.5848. Min Act: -0.0000

Data Index: 401990 (C4 (Web Text))

Max Activating Token Index: 759

Text #5

Max Range: 0.8249. Min Range: -0.8249

Max Act: 0.5401. Min Act: -0.0000

Data Index: 922475 (C4 (Web Text))

Max Activating Token Index: 483

Text #6

Max Range: 0.8249. Min Range: -0.8249

Max Act: 0.5229. Min Act: -0.0000

Data Index: 1307067 (C4 (Web Text))

Max Activating Token Index: 968

Text #7

Max Range: 0.8249. Min Range: -0.8249

Max Act: 0.4634. Min Act: -0.0000

Data Index: 334318 (C4 (Web Text))

Max Activating Token Index: 939

Text #8

Max Range: 0.8249. Min Range: -0.8249

Max Act: 0.4690. Min Act: -0.0000

Data Index: 1065883 (C4 (Web Text))

Max Activating Token Index: 823

Text #9

Max Range: 0.8249. Min Range: -0.8249

Max Act: 0.5005. Min Act: -0.0000

Data Index: 634021 (C4 (Web Text))

Max Activating Token Index: 702

Text #10

Max Range: 0.8249. Min Range: -0.8249

Max Act: 0.4630. Min Act: -0.0000

Data Index: 823927 (C4 (Web Text))

Max Activating Token Index: 122

Text #11

Max Range: 0.8249. Min Range: -0.8249

Max Act: 0.4629. Min Act: -0.0000

Data Index: 1344004 (C4 (Web Text))

Max Activating Token Index: 82

Text #12

Max Range: 0.8249. Min Range: -0.8249

Max Act: 0.4768. Min Act: -0.0000

Data Index: 906658 (C4 (Web Text))

Max Activating Token Index: 902

Text #13

Max Range: 0.8249. Min Range: -0.8249

Max Act: 0.4751. Min Act: -0.0000

Data Index: 53031 (C4 (Web Text))

Max Activating Token Index: 898

Text #14

Max Range: 0.8249. Min Range: -0.8249

Max Act: 0.4265. Min Act: -0.0000

Data Index: 608455 (C4 (Web Text))

Max Activating Token Index: 576

Text #15

Max Range: 0.8249. Min Range: -0.8249

Max Act: 0.4701. Min Act: -0.0000

Data Index: 1151252 (C4 (Web Text))

Max Activating Token Index: 281

Text #16

Max Range: 0.8249. Min Range: -0.8249

Max Act: 0.4543. Min Act: -0.0000

Data Index: 381366 (C4 (Web Text))

Max Activating Token Index: 918

Text #17

Max Range: 0.8249. Min Range: -0.8249

Max Act: 0.4373. Min Act: -0.0000

Data Index: 87093 (C4 (Web Text))

Max Activating Token Index: 840

Text #18

Max Range: 0.8249. Min Range: -0.8249

Max Act: 0.4377. Min Act: -0.0000

Data Index: 807127 (C4 (Web Text))

Max Activating Token Index: 546

Text #19

Max Range: 0.8249. Min Range: -0.8249

Max Act: 0.4270. Min Act: -0.0000

Data Index: 432038 (C4 (Web Text))

Max Activating Token Index: 746