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

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

Neuron 4639 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 1.8334. Min Range: -1.8334

Max Act: 1.8334. Min Act: -0.0002

Data Index: 1239835 (C4 (Web Text))

Max Activating Token Index: 30

Text #1

Max Range: 1.8334. Min Range: -1.8334

Max Act: 1.7888. Min Act: -0.0002

Data Index: 316039 (C4 (Web Text))

Max Activating Token Index: 5

Text #2

Max Range: 1.8334. Min Range: -1.8334

Max Act: 1.7620. Min Act: -0.0002

Data Index: 696810 (C4 (Web Text))

Max Activating Token Index: 7

Text #3

Max Range: 1.8334. Min Range: -1.8334

Max Act: 1.7184. Min Act: -0.0002

Data Index: 190084 (C4 (Web Text))

Max Activating Token Index: 19

Text #4

Max Range: 1.8334. Min Range: -1.8334

Max Act: 1.6579. Min Act: -0.0002

Data Index: 932624 (C4 (Web Text))

Max Activating Token Index: 32

Text #5

Max Range: 1.8334. Min Range: -1.8334

Max Act: 1.6711. Min Act: -0.0002

Data Index: 1087260 (C4 (Web Text))

Max Activating Token Index: 23

Text #6

Max Range: 1.8334. Min Range: -1.8334

Max Act: 1.6425. Min Act: -0.0002

Data Index: 332468 (C4 (Web Text))

Max Activating Token Index: 13

Text #7

Max Range: 1.8334. Min Range: -1.8334

Max Act: 1.6349. Min Act: -0.0002

Data Index: 857773 (C4 (Web Text))

Max Activating Token Index: 38

Text #8

Max Range: 1.8334. Min Range: -1.8334

Max Act: 1.6338. Min Act: -0.0002

Data Index: 846584 (C4 (Web Text))

Max Activating Token Index: 28

Text #9

Max Range: 1.8334. Min Range: -1.8334

Max Act: 1.5891. Min Act: -0.0002

Data Index: 396174 (C4 (Web Text))

Max Activating Token Index: 195

Text #10

Max Range: 1.8334. Min Range: -1.8334

Max Act: 1.5814. Min Act: -0.0002

Data Index: 640686 (C4 (Web Text))

Max Activating Token Index: 673

Text #11

Max Range: 1.8334. Min Range: -1.8334

Max Act: 1.6196. Min Act: -0.0002

Data Index: 449699 (C4 (Web Text))

Max Activating Token Index: 746

Text #12

Max Range: 1.8334. Min Range: -1.8334

Max Act: 1.5905. Min Act: -0.0002

Data Index: 164070 (C4 (Web Text))

Max Activating Token Index: 487

Text #13

Max Range: 1.8334. Min Range: -1.8334

Max Act: 1.6167. Min Act: -0.0002

Data Index: 821761 (C4 (Web Text))

Max Activating Token Index: 7

Text #14

Max Range: 1.8334. Min Range: -1.8334

Max Act: 1.5965. Min Act: -0.0002

Data Index: 1153409 (C4 (Web Text))

Max Activating Token Index: 475

Text #15

Max Range: 1.8334. Min Range: -1.8334

Max Act: 1.5645. Min Act: -0.0002

Data Index: 554632 (C4 (Web Text))

Max Activating Token Index: 2

Text #16

Max Range: 1.8334. Min Range: -1.8334

Max Act: 1.5426. Min Act: -0.0002

Data Index: 1173835 (C4 (Web Text))

Max Activating Token Index: 8

Text #17

Max Range: 1.8334. Min Range: -1.8334

Max Act: 1.5902. Min Act: -0.0002

Data Index: 81848 (C4 (Web Text))

Max Activating Token Index: 79

Text #18

Max Range: 1.8334. Min Range: -1.8334

Max Act: 1.5846. Min Act: -0.0002

Data Index: 319266 (C4 (Web Text))

Max Activating Token Index: 22

Text #19

Max Range: 1.8334. Min Range: -1.8334

Max Act: 1.5348. Min Act: -0.0002

Data Index: 59722 (C4 (Web Text))

Max Activating Token Index: 646