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

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

Neuron 1152 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: 0.7848. Min Range: -0.7848

Max Act: 0.7813. Min Act: -0.0000

Data Index: 343300 (C4 (Web Text))

Max Activating Token Index: 1000

Text #1

Max Range: 0.7848. Min Range: -0.7848

Max Act: 0.7848. Min Act: -0.0000

Data Index: 1182982 (C4 (Web Text))

Max Activating Token Index: 790

Text #2

Max Range: 0.7848. Min Range: -0.7848

Max Act: 0.6096. Min Act: -0.0000

Data Index: 139288 (C4 (Web Text))

Max Activating Token Index: 528

Text #3

Max Range: 0.7848. Min Range: -0.7848

Max Act: 0.6100. Min Act: -0.0000

Data Index: 472221 (C4 (Web Text))

Max Activating Token Index: 968

Text #4

Max Range: 0.7848. Min Range: -0.7848

Max Act: 0.5882. Min Act: -0.0000

Data Index: 163121 (C4 (Web Text))

Max Activating Token Index: 503

Text #5

Max Range: 0.7848. Min Range: -0.7848

Max Act: 0.5450. Min Act: -0.0000

Data Index: 1295743 (C4 (Web Text))

Max Activating Token Index: 694

Text #6

Max Range: 0.7848. Min Range: -0.7848

Max Act: 0.5162. Min Act: -0.0000

Data Index: 1139713 (C4 (Web Text))

Max Activating Token Index: 707

Text #7

Max Range: 0.7848. Min Range: -0.7848

Max Act: 0.5171. Min Act: -0.0000

Data Index: 652706 (C4 (Web Text))

Max Activating Token Index: 88

Text #8

Max Range: 0.7848. Min Range: -0.7848

Max Act: 0.4883. Min Act: -0.0000

Data Index: 874141 (C4 (Web Text))

Max Activating Token Index: 743

Text #9

Max Range: 0.7848. Min Range: -0.7848

Max Act: 0.4990. Min Act: -0.0000

Data Index: 1324961 (C4 (Web Text))

Max Activating Token Index: 284

Text #10

Max Range: 0.7848. Min Range: -0.7848

Max Act: 0.4490. Min Act: -0.0000

Data Index: 138526 (C4 (Web Text))

Max Activating Token Index: 327

Text #11

Max Range: 0.7848. Min Range: -0.7848

Max Act: 0.4719. Min Act: -0.0000

Data Index: 20036 (C4 (Web Text))

Max Activating Token Index: 581

Text #12

Max Range: 0.7848. Min Range: -0.7848

Max Act: 0.4714. Min Act: -0.0000

Data Index: 859449 (C4 (Web Text))

Max Activating Token Index: 120

Text #13

Max Range: 0.7848. Min Range: -0.7848

Max Act: 0.4529. Min Act: -0.0000

Data Index: 226494 (C4 (Web Text))

Max Activating Token Index: 904

Text #14

Max Range: 0.7848. Min Range: -0.7848

Max Act: 0.4350. Min Act: -0.0000

Data Index: 465796 (C4 (Web Text))

Max Activating Token Index: 156

Text #15

Max Range: 0.7848. Min Range: -0.7848

Max Act: 0.4298. Min Act: -0.0000

Data Index: 329720 (C4 (Web Text))

Max Activating Token Index: 634

Text #16

Max Range: 0.7848. Min Range: -0.7848

Max Act: 0.4417. Min Act: -0.0000

Data Index: 642871 (C4 (Web Text))

Max Activating Token Index: 720

Text #17

Max Range: 0.7848. Min Range: -0.7848

Max Act: 0.4220. Min Act: -0.0000

Data Index: 718135 (C4 (Web Text))

Max Activating Token Index: 478

Text #18

Max Range: 0.7848. Min Range: -0.7848

Max Act: 0.4647. Min Act: -0.0000

Data Index: 1175691 (C4 (Web Text))

Max Activating Token Index: 600

Text #19

Max Range: 0.7848. Min Range: -0.7848

Max Act: 0.4354. Min Act: -0.0000

Data Index: 624906 (C4 (Web Text))

Max Activating Token Index: 771