Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2863 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3424. Min Range: -0.3424

Max Act: 0.3424. Min Act: -0.0000

Data Index: 346897 (C4 (Web Text))

Max Activating Token Index: 324

Text #1

Max Range: 0.3424. Min Range: -0.3424

Max Act: 0.3115. Min Act: -0.0001

Data Index: 830651 (C4 (Web Text))

Max Activating Token Index: 806

Text #2

Max Range: 0.3424. Min Range: -0.3424

Max Act: 0.2921. Min Act: -0.0000

Data Index: 736679 (C4 (Web Text))

Max Activating Token Index: 958

Text #3

Max Range: 0.3424. Min Range: -0.3424

Max Act: 0.2711. Min Act: -0.0001

Data Index: 527535 (C4 (Web Text))

Max Activating Token Index: 1009

Text #4

Max Range: 0.3424. Min Range: -0.3424

Max Act: 0.2627. Min Act: -0.0000

Data Index: 200286 (C4 (Web Text))

Max Activating Token Index: 825

Text #5

Max Range: 0.3424. Min Range: -0.3424

Max Act: 0.2724. Min Act: -0.0001

Data Index: 59694 (C4 (Web Text))

Max Activating Token Index: 1017

Text #6

Max Range: 0.3424. Min Range: -0.3424

Max Act: 0.2696. Min Act: -0.0000

Data Index: 831888 (C4 (Web Text))

Max Activating Token Index: 1002

Text #7

Max Range: 0.3424. Min Range: -0.3424

Max Act: 0.2457. Min Act: -0.0001

Data Index: 1326333 (C4 (Web Text))

Max Activating Token Index: 521

Text #8

Max Range: 0.3424. Min Range: -0.3424

Max Act: 0.2525. Min Act: -0.0000

Data Index: 593688 (C4 (Web Text))

Max Activating Token Index: 992

Text #9

Max Range: 0.3424. Min Range: -0.3424

Max Act: 0.2526. Min Act: -0.0001

Data Index: 44743 (C4 (Web Text))

Max Activating Token Index: 874

Text #10

Max Range: 0.3424. Min Range: -0.3424

Max Act: 0.2594. Min Act: -0.0000

Data Index: 420692 (C4 (Web Text))

Max Activating Token Index: 668

Text #11

Max Range: 0.3424. Min Range: -0.3424

Max Act: 0.2400. Min Act: -0.0000

Data Index: 1272896 (C4 (Web Text))

Max Activating Token Index: 867

Text #12

Max Range: 0.3424. Min Range: -0.3424

Max Act: 0.2451. Min Act: -0.0001

Data Index: 326188 (C4 (Web Text))

Max Activating Token Index: 50

Text #13

Max Range: 0.3424. Min Range: -0.3424

Max Act: 0.2334. Min Act: -0.0000

Data Index: 742581 (C4 (Web Text))

Max Activating Token Index: 850

Text #14

Max Range: 0.3424. Min Range: -0.3424

Max Act: 0.2482. Min Act: -0.0001

Data Index: 854106 (C4 (Web Text))

Max Activating Token Index: 74

Text #15

Max Range: 0.3424. Min Range: -0.3424

Max Act: 0.2257. Min Act: -0.0001

Data Index: 1321732 (C4 (Web Text))

Max Activating Token Index: 630

Text #16

Max Range: 0.3424. Min Range: -0.3424

Max Act: 0.2388. Min Act: -0.0000

Data Index: 329255 (C4 (Web Text))

Max Activating Token Index: 881

Text #17

Max Range: 0.3424. Min Range: -0.3424

Max Act: 0.2384. Min Act: -0.0000

Data Index: 436002 (C4 (Web Text))

Max Activating Token Index: 1020

Text #18

Max Range: 0.3424. Min Range: -0.3424

Max Act: 0.2387. Min Act: -0.0000

Data Index: 717188 (C4 (Web Text))

Max Activating Token Index: 158

Text #19

Max Range: 0.3424. Min Range: -0.3424

Max Act: 0.2380. Min Act: -0.0001

Data Index: 115970 (C4 (Web Text))

Max Activating Token Index: 424