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

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

Neuron 639 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: 1.1460. Min Range: -1.1460

Max Act: 1.1460. Min Act: -0.0002

Data Index: 1353693 (C4 (Web Text))

Max Activating Token Index: 10

Text #1

Max Range: 1.1460. Min Range: -1.1460

Max Act: 1.0854. Min Act: -0.0002

Data Index: 671153 (C4 (Web Text))

Max Activating Token Index: 331

Text #2

Max Range: 1.1460. Min Range: -1.1460

Max Act: 1.0881. Min Act: -0.0002

Data Index: 879552 (C4 (Web Text))

Max Activating Token Index: 31

Text #3

Max Range: 1.1460. Min Range: -1.1460

Max Act: 1.0775. Min Act: -0.0002

Data Index: 739277 (C4 (Web Text))

Max Activating Token Index: 60

Text #4

Max Range: 1.1460. Min Range: -1.1460

Max Act: 1.0586. Min Act: -0.0002

Data Index: 1347732 (C4 (Web Text))

Max Activating Token Index: 66

Text #5

Max Range: 1.1460. Min Range: -1.1460

Max Act: 1.0859. Min Act: -0.0002

Data Index: 1341965 (C4 (Web Text))

Max Activating Token Index: 206

Text #6

Max Range: 1.1460. Min Range: -1.1460

Max Act: 1.0553. Min Act: -0.0002

Data Index: 688411 (C4 (Web Text))

Max Activating Token Index: 408

Text #7

Max Range: 1.1460. Min Range: -1.1460

Max Act: 1.0417. Min Act: -0.0002

Data Index: 267125 (C4 (Web Text))

Max Activating Token Index: 8

Text #8

Max Range: 1.1460. Min Range: -1.1460

Max Act: 1.0375. Min Act: -0.0002

Data Index: 144198 (C4 (Web Text))

Max Activating Token Index: 674

Text #9

Max Range: 1.1460. Min Range: -1.1460

Max Act: 1.0536. Min Act: -0.0002

Data Index: 455155 (C4 (Web Text))

Max Activating Token Index: 71

Text #10

Max Range: 1.1460. Min Range: -1.1460

Max Act: 1.0515. Min Act: -0.0002

Data Index: 1347680 (C4 (Web Text))

Max Activating Token Index: 18

Text #11

Max Range: 1.1460. Min Range: -1.1460

Max Act: 1.0111. Min Act: -0.0002

Data Index: 583384 (C4 (Web Text))

Max Activating Token Index: 6

Text #12

Max Range: 1.1460. Min Range: -1.1460

Max Act: 1.0213. Min Act: -0.0002

Data Index: 330594 (C4 (Web Text))

Max Activating Token Index: 100

Text #13

Max Range: 1.1460. Min Range: -1.1460

Max Act: 1.0156. Min Act: -0.0002

Data Index: 303634 (C4 (Web Text))

Max Activating Token Index: 41

Text #14

Max Range: 1.1460. Min Range: -1.1460

Max Act: 1.0201. Min Act: -0.0002

Data Index: 1245658 (C4 (Web Text))

Max Activating Token Index: 268

Text #15

Max Range: 1.1460. Min Range: -1.1460

Max Act: 0.9849. Min Act: -0.0002

Data Index: 1180994 (C4 (Web Text))

Max Activating Token Index: 7

Text #16

Max Range: 1.1460. Min Range: -1.1460

Max Act: 0.9934. Min Act: -0.0002

Data Index: 887520 (C4 (Web Text))

Max Activating Token Index: 162

Text #17

Max Range: 1.1460. Min Range: -1.1460

Max Act: 0.9962. Min Act: -0.0002

Data Index: 922707 (C4 (Web Text))

Max Activating Token Index: 162

Text #18

Max Range: 1.1460. Min Range: -1.1460

Max Act: 0.9834. Min Act: -0.0002

Data Index: 80707 (C4 (Web Text))

Max Activating Token Index: 5

Text #19

Max Range: 1.1460. Min Range: -1.1460

Max Act: 0.9868. Min Act: -0.0002

Data Index: 1047715 (C4 (Web Text))

Max Activating Token Index: 133