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

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

Neuron 3661 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4632. Min Range: -1.4632

Max Act: 1.3875. Min Act: -0.0000

Data Index: 229802 (C4 (Web Text))

Max Activating Token Index: 770

Text #1

Max Range: 1.4632. Min Range: -1.4632

Max Act: 1.4632. Min Act: -0.0000

Data Index: 230466 (C4 (Web Text))

Max Activating Token Index: 202

Text #2

Max Range: 1.4632. Min Range: -1.4632

Max Act: 1.3791. Min Act: -0.0000

Data Index: 1344660 (C4 (Web Text))

Max Activating Token Index: 1021

Text #3

Max Range: 1.4632. Min Range: -1.4632

Max Act: 1.2830. Min Act: -0.0000

Data Index: 1613365 (Python Code)

Max Activating Token Index: 631

Text #4

Max Range: 1.4632. Min Range: -1.4632

Max Act: 1.1856. Min Act: -0.0000

Data Index: 889045 (C4 (Web Text))

Max Activating Token Index: 727

Text #5

Max Range: 1.4632. Min Range: -1.4632

Max Act: 1.2360. Min Act: -0.0001

Data Index: 654607 (C4 (Web Text))

Max Activating Token Index: 1014

Text #6

Max Range: 1.4632. Min Range: -1.4632

Max Act: 1.0597. Min Act: -0.0000

Data Index: 197563 (C4 (Web Text))

Max Activating Token Index: 742

Text #7

Max Range: 1.4632. Min Range: -1.4632

Max Act: 1.1421. Min Act: -0.0000

Data Index: 896770 (C4 (Web Text))

Max Activating Token Index: 210

Text #8

Max Range: 1.4632. Min Range: -1.4632

Max Act: 1.0318. Min Act: -0.0000

Data Index: 600603 (C4 (Web Text))

Max Activating Token Index: 950

Text #9

Max Range: 1.4632. Min Range: -1.4632

Max Act: 1.0295. Min Act: -0.0000

Data Index: 1225275 (C4 (Web Text))

Max Activating Token Index: 453

Text #10

Max Range: 1.4632. Min Range: -1.4632

Max Act: 1.0269. Min Act: -0.0000

Data Index: 140443 (C4 (Web Text))

Max Activating Token Index: 994

Text #11

Max Range: 1.4632. Min Range: -1.4632

Max Act: 1.0475. Min Act: -0.0000

Data Index: 758136 (C4 (Web Text))

Max Activating Token Index: 935

Text #12

Max Range: 1.4632. Min Range: -1.4632

Max Act: 1.0366. Min Act: -0.0001

Data Index: 1583660 (Python Code)

Max Activating Token Index: 706

Text #13

Max Range: 1.4632. Min Range: -1.4632

Max Act: 1.0368. Min Act: -0.0000

Data Index: 629767 (C4 (Web Text))

Max Activating Token Index: 700

Text #14

Max Range: 1.4632. Min Range: -1.4632

Max Act: 0.9746. Min Act: -0.0000

Data Index: 670956 (C4 (Web Text))

Max Activating Token Index: 647

Text #15

Max Range: 1.4632. Min Range: -1.4632

Max Act: 0.8878. Min Act: -0.0000

Data Index: 194641 (C4 (Web Text))

Max Activating Token Index: 402

Text #16

Max Range: 1.4632. Min Range: -1.4632

Max Act: 0.9610. Min Act: -0.0000

Data Index: 1446619 (Python Code)

Max Activating Token Index: 599

Text #17

Max Range: 1.4632. Min Range: -1.4632

Max Act: 0.9670. Min Act: -0.0000

Data Index: 42 (C4 (Web Text))

Max Activating Token Index: 469

Text #18

Max Range: 1.4632. Min Range: -1.4632

Max Act: 0.9390. Min Act: -0.0001

Data Index: 1312575 (C4 (Web Text))

Max Activating Token Index: 637

Text #19

Max Range: 1.4632. Min Range: -1.4632

Max Act: 0.9548. Min Act: -0.0000

Data Index: 1101490 (C4 (Web Text))

Max Activating Token Index: 492