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

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

Neuron 3606 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.4789. Min Range: -0.4789

Max Act: 0.4614. Min Act: -0.0000

Data Index: 162337 (C4 (Web Text))

Max Activating Token Index: 666

Text #1

Max Range: 0.4789. Min Range: -0.4789

Max Act: 0.4789. Min Act: -0.0000

Data Index: 1122746 (C4 (Web Text))

Max Activating Token Index: 805

Text #2

Max Range: 0.4789. Min Range: -0.4789

Max Act: 0.4692. Min Act: -0.0000

Data Index: 868955 (C4 (Web Text))

Max Activating Token Index: 74

Text #3

Max Range: 0.4789. Min Range: -0.4789

Max Act: 0.4180. Min Act: -0.0000

Data Index: 158101 (C4 (Web Text))

Max Activating Token Index: 437

Text #4

Max Range: 0.4789. Min Range: -0.4789

Max Act: 0.4015. Min Act: -0.0000

Data Index: 116457 (C4 (Web Text))

Max Activating Token Index: 395

Text #5

Max Range: 0.4789. Min Range: -0.4789

Max Act: 0.4007. Min Act: -0.0000

Data Index: 903594 (C4 (Web Text))

Max Activating Token Index: 342

Text #6

Max Range: 0.4789. Min Range: -0.4789

Max Act: 0.3985. Min Act: -0.0000

Data Index: 638359 (C4 (Web Text))

Max Activating Token Index: 578

Text #7

Max Range: 0.4789. Min Range: -0.4789

Max Act: 0.3714. Min Act: -0.0000

Data Index: 1143416 (C4 (Web Text))

Max Activating Token Index: 239

Text #8

Max Range: 0.4789. Min Range: -0.4789

Max Act: 0.3709. Min Act: -0.0000

Data Index: 1088031 (C4 (Web Text))

Max Activating Token Index: 217

Text #9

Max Range: 0.4789. Min Range: -0.4789

Max Act: 0.3607. Min Act: -0.0000

Data Index: 1345921 (C4 (Web Text))

Max Activating Token Index: 17

Text #10

Max Range: 0.4789. Min Range: -0.4789

Max Act: 0.3653. Min Act: -0.0000

Data Index: 507532 (C4 (Web Text))

Max Activating Token Index: 689

Text #11

Max Range: 0.4789. Min Range: -0.4789

Max Act: 0.3527. Min Act: -0.0000

Data Index: 1133983 (C4 (Web Text))

Max Activating Token Index: 746

Text #12

Max Range: 0.4789. Min Range: -0.4789

Max Act: 0.3292. Min Act: -0.0000

Data Index: 1189288 (C4 (Web Text))

Max Activating Token Index: 801

Text #13

Max Range: 0.4789. Min Range: -0.4789

Max Act: 0.3501. Min Act: -0.0000

Data Index: 195413 (C4 (Web Text))

Max Activating Token Index: 498

Text #14

Max Range: 0.4789. Min Range: -0.4789

Max Act: 0.3478. Min Act: -0.0000

Data Index: 653142 (C4 (Web Text))

Max Activating Token Index: 473

Text #15

Max Range: 0.4789. Min Range: -0.4789

Max Act: 0.3238. Min Act: -0.0000

Data Index: 587645 (C4 (Web Text))

Max Activating Token Index: 871

Text #16

Max Range: 0.4789. Min Range: -0.4789

Max Act: 0.3321. Min Act: -0.0000

Data Index: 1044961 (C4 (Web Text))

Max Activating Token Index: 890

Text #17

Max Range: 0.4789. Min Range: -0.4789

Max Act: 0.3507. Min Act: -0.0000

Data Index: 1035729 (C4 (Web Text))

Max Activating Token Index: 330

Text #18

Max Range: 0.4789. Min Range: -0.4789

Max Act: 0.3268. Min Act: -0.0000

Data Index: 1047543 (C4 (Web Text))

Max Activating Token Index: 350

Text #19

Max Range: 0.4789. Min Range: -0.4789

Max Act: 0.3165. Min Act: -0.0000

Data Index: 120876 (C4 (Web Text))

Max Activating Token Index: 575