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

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

Neuron 2921 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: 0.4870. Min Range: -0.4870

Max Act: 0.4870. Min Act: -0.0000

Data Index: 944252 (C4 (Web Text))

Max Activating Token Index: 158

Text #1

Max Range: 0.4870. Min Range: -0.4870

Max Act: 0.4579. Min Act: -0.0000

Data Index: 82775 (C4 (Web Text))

Max Activating Token Index: 524

Text #2

Max Range: 0.4870. Min Range: -0.4870

Max Act: 0.4144. Min Act: -0.0000

Data Index: 1277106 (C4 (Web Text))

Max Activating Token Index: 475

Text #3

Max Range: 0.4870. Min Range: -0.4870

Max Act: 0.4197. Min Act: -0.0000

Data Index: 729301 (C4 (Web Text))

Max Activating Token Index: 688

Text #4

Max Range: 0.4870. Min Range: -0.4870

Max Act: 0.4254. Min Act: -0.0000

Data Index: 23908 (C4 (Web Text))

Max Activating Token Index: 177

Text #5

Max Range: 0.4870. Min Range: -0.4870

Max Act: 0.3842. Min Act: -0.0000

Data Index: 144332 (C4 (Web Text))

Max Activating Token Index: 489

Text #6

Max Range: 0.4870. Min Range: -0.4870

Max Act: 0.3808. Min Act: 0.0000

Data Index: 491416 (C4 (Web Text))

Max Activating Token Index: 484

Text #7

Max Range: 0.4870. Min Range: -0.4870

Max Act: 0.3923. Min Act: -0.0000

Data Index: 704687 (C4 (Web Text))

Max Activating Token Index: 981

Text #8

Max Range: 0.4870. Min Range: -0.4870

Max Act: 0.3493. Min Act: -0.0000

Data Index: 880345 (C4 (Web Text))

Max Activating Token Index: 645

Text #9

Max Range: 0.4870. Min Range: -0.4870

Max Act: 0.3558. Min Act: -0.0000

Data Index: 1616947 (Python Code)

Max Activating Token Index: 243

Text #10

Max Range: 0.4870. Min Range: -0.4870

Max Act: 0.3735. Min Act: -0.0000

Data Index: 1350015 (C4 (Web Text))

Max Activating Token Index: 176

Text #11

Max Range: 0.4870. Min Range: -0.4870

Max Act: 0.3403. Min Act: -0.0000

Data Index: 1490601 (Python Code)

Max Activating Token Index: 147

Text #12

Max Range: 0.4870. Min Range: -0.4870

Max Act: 0.3663. Min Act: -0.0000

Data Index: 1233361 (C4 (Web Text))

Max Activating Token Index: 120

Text #13

Max Range: 0.4870. Min Range: -0.4870

Max Act: 0.3572. Min Act: -0.0000

Data Index: 1331304 (C4 (Web Text))

Max Activating Token Index: 83

Text #14

Max Range: 0.4870. Min Range: -0.4870

Max Act: 0.3565. Min Act: 0.0000

Data Index: 771436 (C4 (Web Text))

Max Activating Token Index: 172

Text #15

Max Range: 0.4870. Min Range: -0.4870

Max Act: 0.3562. Min Act: -0.0000

Data Index: 942975 (C4 (Web Text))

Max Activating Token Index: 467

Text #16

Max Range: 0.4870. Min Range: -0.4870

Max Act: 0.3575. Min Act: -0.0000

Data Index: 265298 (C4 (Web Text))

Max Activating Token Index: 313

Text #17

Max Range: 0.4870. Min Range: -0.4870

Max Act: 0.3471. Min Act: 0.0000

Data Index: 1053096 (C4 (Web Text))

Max Activating Token Index: 349

Text #18

Max Range: 0.4870. Min Range: -0.4870

Max Act: 0.3292. Min Act: -0.0000

Data Index: 1055399 (C4 (Web Text))

Max Activating Token Index: 180

Text #19

Max Range: 0.4870. Min Range: -0.4870

Max Act: 0.3625. Min Act: -0.0000

Data Index: 1020479 (C4 (Web Text))

Max Activating Token Index: 477