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

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

Neuron 5304 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6125. Min Range: -0.6125

Max Act: 0.6125. Min Act: -0.0000

Data Index: 694112 (C4 (Web Text))

Max Activating Token Index: 391

Text #1

Max Range: 0.6125. Min Range: -0.6125

Max Act: 0.5740. Min Act: -0.0000

Data Index: 724009 (C4 (Web Text))

Max Activating Token Index: 971

Text #2

Max Range: 0.6125. Min Range: -0.6125

Max Act: 0.5437. Min Act: -0.0000

Data Index: 720945 (C4 (Web Text))

Max Activating Token Index: 1022

Text #3

Max Range: 0.6125. Min Range: -0.6125

Max Act: 0.5391. Min Act: -0.0000

Data Index: 1028947 (C4 (Web Text))

Max Activating Token Index: 143

Text #4

Max Range: 0.6125. Min Range: -0.6125

Max Act: 0.5661. Min Act: -0.0000

Data Index: 173734 (C4 (Web Text))

Max Activating Token Index: 970

Text #5

Max Range: 0.6125. Min Range: -0.6125

Max Act: 0.5062. Min Act: -0.0000

Data Index: 1001015 (C4 (Web Text))

Max Activating Token Index: 657

Text #6

Max Range: 0.6125. Min Range: -0.6125

Max Act: 0.4868. Min Act: -0.0000

Data Index: 236810 (C4 (Web Text))

Max Activating Token Index: 166

Text #7

Max Range: 0.6125. Min Range: -0.6125

Max Act: 0.4807. Min Act: -0.0000

Data Index: 98439 (C4 (Web Text))

Max Activating Token Index: 594

Text #8

Max Range: 0.6125. Min Range: -0.6125

Max Act: 0.4610. Min Act: -0.0000

Data Index: 856933 (C4 (Web Text))

Max Activating Token Index: 569

Text #9

Max Range: 0.6125. Min Range: -0.6125

Max Act: 0.4712. Min Act: -0.0000

Data Index: 518411 (C4 (Web Text))

Max Activating Token Index: 342

Text #10

Max Range: 0.6125. Min Range: -0.6125

Max Act: 0.4521. Min Act: -0.0000

Data Index: 872367 (C4 (Web Text))

Max Activating Token Index: 787

Text #11

Max Range: 0.6125. Min Range: -0.6125

Max Act: 0.4649. Min Act: -0.0000

Data Index: 933058 (C4 (Web Text))

Max Activating Token Index: 66

Text #12

Max Range: 0.6125. Min Range: -0.6125

Max Act: 0.4761. Min Act: -0.0000

Data Index: 937023 (C4 (Web Text))

Max Activating Token Index: 493

Text #13

Max Range: 0.6125. Min Range: -0.6125

Max Act: 0.4090. Min Act: -0.0000

Data Index: 1341415 (C4 (Web Text))

Max Activating Token Index: 549

Text #14

Max Range: 0.6125. Min Range: -0.6125

Max Act: 0.4536. Min Act: -0.0000

Data Index: 718565 (C4 (Web Text))

Max Activating Token Index: 424

Text #15

Max Range: 0.6125. Min Range: -0.6125

Max Act: 0.5156. Min Act: -0.0000

Data Index: 347203 (C4 (Web Text))

Max Activating Token Index: 909

Text #16

Max Range: 0.6125. Min Range: -0.6125

Max Act: 0.4684. Min Act: -0.0000

Data Index: 271731 (C4 (Web Text))

Max Activating Token Index: 408

Text #17

Max Range: 0.6125. Min Range: -0.6125

Max Act: 0.4294. Min Act: -0.0000

Data Index: 210505 (C4 (Web Text))

Max Activating Token Index: 632

Text #18

Max Range: 0.6125. Min Range: -0.6125

Max Act: 0.4390. Min Act: -0.0000

Data Index: 274533 (C4 (Web Text))

Max Activating Token Index: 797

Text #19

Max Range: 0.6125. Min Range: -0.6125

Max Act: 0.3845. Min Act: -0.0000

Data Index: 930012 (C4 (Web Text))

Max Activating Token Index: 361