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

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

Neuron 1435 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: 0.7000. Min Range: -0.7000

Max Act: 0.7000. Min Act: -0.0000

Data Index: 460774 (C4 (Web Text))

Max Activating Token Index: 635

Text #1

Max Range: 0.7000. Min Range: -0.7000

Max Act: 0.6355. Min Act: -0.0000

Data Index: 121767 (C4 (Web Text))

Max Activating Token Index: 17

Text #2

Max Range: 0.7000. Min Range: -0.7000

Max Act: 0.6256. Min Act: -0.0000

Data Index: 1138758 (C4 (Web Text))

Max Activating Token Index: 368

Text #3

Max Range: 0.7000. Min Range: -0.7000

Max Act: 0.5615. Min Act: -0.0000

Data Index: 158797 (C4 (Web Text))

Max Activating Token Index: 85

Text #4

Max Range: 0.7000. Min Range: -0.7000

Max Act: 0.5572. Min Act: -0.0000

Data Index: 1175110 (C4 (Web Text))

Max Activating Token Index: 916

Text #5

Max Range: 0.7000. Min Range: -0.7000

Max Act: 0.5410. Min Act: -0.0000

Data Index: 834379 (C4 (Web Text))

Max Activating Token Index: 391

Text #6

Max Range: 0.7000. Min Range: -0.7000

Max Act: 0.5431. Min Act: -0.0000

Data Index: 1092138 (C4 (Web Text))

Max Activating Token Index: 449

Text #7

Max Range: 0.7000. Min Range: -0.7000

Max Act: 0.5578. Min Act: -0.0000

Data Index: 365809 (C4 (Web Text))

Max Activating Token Index: 952

Text #8

Max Range: 0.7000. Min Range: -0.7000

Max Act: 0.5250. Min Act: -0.0000

Data Index: 254842 (C4 (Web Text))

Max Activating Token Index: 459

Text #9

Max Range: 0.7000. Min Range: -0.7000

Max Act: 0.5138. Min Act: -0.0000

Data Index: 766644 (C4 (Web Text))

Max Activating Token Index: 595

Text #10

Max Range: 0.7000. Min Range: -0.7000

Max Act: 0.5291. Min Act: -0.0000

Data Index: 136867 (C4 (Web Text))

Max Activating Token Index: 402

Text #11

Max Range: 0.7000. Min Range: -0.7000

Max Act: 0.5267. Min Act: -0.0000

Data Index: 225940 (C4 (Web Text))

Max Activating Token Index: 988

Text #12

Max Range: 0.7000. Min Range: -0.7000

Max Act: 0.5349. Min Act: -0.0000

Data Index: 177679 (C4 (Web Text))

Max Activating Token Index: 800

Text #13

Max Range: 0.7000. Min Range: -0.7000

Max Act: 0.4938. Min Act: -0.0000

Data Index: 361530 (C4 (Web Text))

Max Activating Token Index: 359

Text #14

Max Range: 0.7000. Min Range: -0.7000

Max Act: 0.4885. Min Act: -0.0000

Data Index: 489624 (C4 (Web Text))

Max Activating Token Index: 778

Text #15

Max Range: 0.7000. Min Range: -0.7000

Max Act: 0.4673. Min Act: -0.0000

Data Index: 437811 (C4 (Web Text))

Max Activating Token Index: 64

Text #16

Max Range: 0.7000. Min Range: -0.7000

Max Act: 0.4836. Min Act: -0.0000

Data Index: 758791 (C4 (Web Text))

Max Activating Token Index: 487

Text #17

Max Range: 0.7000. Min Range: -0.7000

Max Act: 0.4479. Min Act: -0.0000

Data Index: 477153 (C4 (Web Text))

Max Activating Token Index: 676

Text #18

Max Range: 0.7000. Min Range: -0.7000

Max Act: 0.4640. Min Act: -0.0000

Data Index: 1300591 (C4 (Web Text))

Max Activating Token Index: 806

Text #19

Max Range: 0.7000. Min Range: -0.7000

Max Act: 0.4862. Min Act: -0.0000

Data Index: 447498 (C4 (Web Text))

Max Activating Token Index: 710