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

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

Neuron 4268 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: 2.1610. Min Range: -2.1610

Max Act: 2.1610. Min Act: -0.0000

Data Index: 1024371 (C4 (Web Text))

Max Activating Token Index: 419

Text #1

Max Range: 2.1610. Min Range: -2.1610

Max Act: 2.0350. Min Act: -0.0000

Data Index: 1716 (C4 (Web Text))

Max Activating Token Index: 183

Text #2

Max Range: 2.1610. Min Range: -2.1610

Max Act: 2.1528. Min Act: -0.0000

Data Index: 177100 (C4 (Web Text))

Max Activating Token Index: 653

Text #3

Max Range: 2.1610. Min Range: -2.1610

Max Act: 1.8854. Min Act: -0.0000

Data Index: 185383 (C4 (Web Text))

Max Activating Token Index: 122

Text #4

Max Range: 2.1610. Min Range: -2.1610

Max Act: 1.9375. Min Act: -0.0000

Data Index: 79331 (C4 (Web Text))

Max Activating Token Index: 578

Text #5

Max Range: 2.1610. Min Range: -2.1610

Max Act: 1.9164. Min Act: -0.0000

Data Index: 790238 (C4 (Web Text))

Max Activating Token Index: 1008

Text #6

Max Range: 2.1610. Min Range: -2.1610

Max Act: 1.8665. Min Act: -0.0000

Data Index: 344462 (C4 (Web Text))

Max Activating Token Index: 583

Text #7

Max Range: 2.1610. Min Range: -2.1610

Max Act: 1.9416. Min Act: -0.0000

Data Index: 674541 (C4 (Web Text))

Max Activating Token Index: 974

Text #8

Max Range: 2.1610. Min Range: -2.1610

Max Act: 1.8498. Min Act: -0.0000

Data Index: 779643 (C4 (Web Text))

Max Activating Token Index: 304

Text #9

Max Range: 2.1610. Min Range: -2.1610

Max Act: 1.6223. Min Act: -0.0000

Data Index: 1617706 (Python Code)

Max Activating Token Index: 765

Text #10

Max Range: 2.1610. Min Range: -2.1610

Max Act: 1.7875. Min Act: -0.0000

Data Index: 1127628 (C4 (Web Text))

Max Activating Token Index: 503

Text #11

Max Range: 2.1610. Min Range: -2.1610

Max Act: 1.7619. Min Act: -0.0000

Data Index: 360557 (C4 (Web Text))

Max Activating Token Index: 716

Text #12

Max Range: 2.1610. Min Range: -2.1610

Max Act: 1.7549. Min Act: -0.0000

Data Index: 823520 (C4 (Web Text))

Max Activating Token Index: 586

Text #13

Max Range: 2.1610. Min Range: -2.1610

Max Act: 1.9356. Min Act: -0.0000

Data Index: 559563 (C4 (Web Text))

Max Activating Token Index: 790

Text #14

Max Range: 2.1610. Min Range: -2.1610

Max Act: 1.7986. Min Act: -0.0000

Data Index: 1518317 (Python Code)

Max Activating Token Index: 924

Text #15

Max Range: 2.1610. Min Range: -2.1610

Max Act: 1.6783. Min Act: -0.0000

Data Index: 865950 (C4 (Web Text))

Max Activating Token Index: 893

Text #16

Max Range: 2.1610. Min Range: -2.1610

Max Act: 1.6881. Min Act: -0.0000

Data Index: 747224 (C4 (Web Text))

Max Activating Token Index: 1000

Text #17

Max Range: 2.1610. Min Range: -2.1610

Max Act: 1.8597. Min Act: -0.0000

Data Index: 528914 (C4 (Web Text))

Max Activating Token Index: 771

Text #18

Max Range: 2.1610. Min Range: -2.1610

Max Act: 1.6554. Min Act: -0.0000

Data Index: 563014 (C4 (Web Text))

Max Activating Token Index: 915

Text #19

Max Range: 2.1610. Min Range: -2.1610

Max Act: 1.6563. Min Act: -0.0000

Data Index: 139467 (C4 (Web Text))

Max Activating Token Index: 727