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

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

Neuron 4193 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9760. Min Range: -0.9760

Max Act: 0.9760. Min Act: -0.0000

Data Index: 1546190 (Python Code)

Max Activating Token Index: 94

Text #1

Max Range: 0.9760. Min Range: -0.9760

Max Act: 0.9098. Min Act: -0.0000

Data Index: 1610248 (Python Code)

Max Activating Token Index: 878

Text #2

Max Range: 0.9760. Min Range: -0.9760

Max Act: 0.8861. Min Act: -0.0000

Data Index: 1450761 (Python Code)

Max Activating Token Index: 339

Text #3

Max Range: 0.9760. Min Range: -0.9760

Max Act: 0.8805. Min Act: -0.0000

Data Index: 1646349 (Python Code)

Max Activating Token Index: 213

Text #4

Max Range: 0.9760. Min Range: -0.9760

Max Act: 0.8624. Min Act: -0.0000

Data Index: 1423228 (Python Code)

Max Activating Token Index: 249

Text #5

Max Range: 0.9760. Min Range: -0.9760

Max Act: 0.8118. Min Act: -0.0000

Data Index: 1478919 (Python Code)

Max Activating Token Index: 727

Text #6

Max Range: 0.9760. Min Range: -0.9760

Max Act: 0.7531. Min Act: -0.0000

Data Index: 435965 (C4 (Web Text))

Max Activating Token Index: 39

Text #7

Max Range: 0.9760. Min Range: -0.9760

Max Act: 0.7486. Min Act: -0.0000

Data Index: 614435 (C4 (Web Text))

Max Activating Token Index: 562

Text #8

Max Range: 0.9760. Min Range: -0.9760

Max Act: 0.7209. Min Act: -0.0000

Data Index: 203292 (C4 (Web Text))

Max Activating Token Index: 234

Text #9

Max Range: 0.9760. Min Range: -0.9760

Max Act: 0.6797. Min Act: -0.0000

Data Index: 637371 (C4 (Web Text))

Max Activating Token Index: 58

Text #10

Max Range: 0.9760. Min Range: -0.9760

Max Act: 0.6608. Min Act: -0.0000

Data Index: 778970 (C4 (Web Text))

Max Activating Token Index: 148

Text #11

Max Range: 0.9760. Min Range: -0.9760

Max Act: 0.6080. Min Act: -0.0000

Data Index: 345158 (C4 (Web Text))

Max Activating Token Index: 915

Text #12

Max Range: 0.9760. Min Range: -0.9760

Max Act: 0.9196. Min Act: -0.0000

Data Index: 651345 (C4 (Web Text))

Max Activating Token Index: 320

Text #13

Max Range: 0.9760. Min Range: -0.9760

Max Act: 0.6617. Min Act: -0.0000

Data Index: 934750 (C4 (Web Text))

Max Activating Token Index: 771

Text #14

Max Range: 0.9760. Min Range: -0.9760

Max Act: 0.7209. Min Act: -0.0000

Data Index: 410840 (C4 (Web Text))

Max Activating Token Index: 24

Text #15

Max Range: 0.9760. Min Range: -0.9760

Max Act: 0.6517. Min Act: -0.0000

Data Index: 1425127 (Python Code)

Max Activating Token Index: 644

Text #16

Max Range: 0.9760. Min Range: -0.9760

Max Act: 0.7686. Min Act: -0.0000

Data Index: 935959 (C4 (Web Text))

Max Activating Token Index: 715

Text #17

Max Range: 0.9760. Min Range: -0.9760

Max Act: 0.6806. Min Act: -0.0000

Data Index: 620 (C4 (Web Text))

Max Activating Token Index: 775

Text #18

Max Range: 0.9760. Min Range: -0.9760

Max Act: 0.6557. Min Act: -0.0000

Data Index: 850005 (C4 (Web Text))

Max Activating Token Index: 973

Text #19

Max Range: 0.9760. Min Range: -0.9760

Max Act: 0.6066. Min Act: -0.0000

Data Index: 1611123 (Python Code)

Max Activating Token Index: 688