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

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

Neuron 3804 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: 1.1648. Min Range: -1.1648

Max Act: 1.1648. Min Act: -0.0000

Data Index: 1190652 (C4 (Web Text))

Max Activating Token Index: 22

Text #1

Max Range: 1.1648. Min Range: -1.1648

Max Act: 1.0955. Min Act: -0.0000

Data Index: 944592 (C4 (Web Text))

Max Activating Token Index: 14

Text #2

Max Range: 1.1648. Min Range: -1.1648

Max Act: 0.9791. Min Act: -0.0000

Data Index: 1312749 (C4 (Web Text))

Max Activating Token Index: 347

Text #3

Max Range: 1.1648. Min Range: -1.1648

Max Act: 1.0185. Min Act: -0.0000

Data Index: 247636 (C4 (Web Text))

Max Activating Token Index: 1005

Text #4

Max Range: 1.1648. Min Range: -1.1648

Max Act: 0.8892. Min Act: -0.0000

Data Index: 245895 (C4 (Web Text))

Max Activating Token Index: 647

Text #5

Max Range: 1.1648. Min Range: -1.1648

Max Act: 1.0187. Min Act: -0.0000

Data Index: 1324549 (C4 (Web Text))

Max Activating Token Index: 486

Text #6

Max Range: 1.1648. Min Range: -1.1648

Max Act: 0.9348. Min Act: -0.0000

Data Index: 398353 (C4 (Web Text))

Max Activating Token Index: 635

Text #7

Max Range: 1.1648. Min Range: -1.1648

Max Act: 0.9380. Min Act: -0.0000

Data Index: 410018 (C4 (Web Text))

Max Activating Token Index: 27

Text #8

Max Range: 1.1648. Min Range: -1.1648

Max Act: 0.8307. Min Act: -0.0000

Data Index: 620047 (C4 (Web Text))

Max Activating Token Index: 206

Text #9

Max Range: 1.1648. Min Range: -1.1648

Max Act: 0.8652. Min Act: -0.0000

Data Index: 1023306 (C4 (Web Text))

Max Activating Token Index: 15

Text #10

Max Range: 1.1648. Min Range: -1.1648

Max Act: 0.8822. Min Act: -0.0000

Data Index: 555406 (C4 (Web Text))

Max Activating Token Index: 9

Text #11

Max Range: 1.1648. Min Range: -1.1648

Max Act: 0.8774. Min Act: -0.0000

Data Index: 48130 (C4 (Web Text))

Max Activating Token Index: 947

Text #12

Max Range: 1.1648. Min Range: -1.1648

Max Act: 0.8226. Min Act: -0.0000

Data Index: 1154731 (C4 (Web Text))

Max Activating Token Index: 178

Text #13

Max Range: 1.1648. Min Range: -1.1648

Max Act: 0.7180. Min Act: -0.0000

Data Index: 768490 (C4 (Web Text))

Max Activating Token Index: 158

Text #14

Max Range: 1.1648. Min Range: -1.1648

Max Act: 0.8090. Min Act: -0.0000

Data Index: 279212 (C4 (Web Text))

Max Activating Token Index: 78

Text #15

Max Range: 1.1648. Min Range: -1.1648

Max Act: 0.8711. Min Act: 0.0000

Data Index: 926996 (C4 (Web Text))

Max Activating Token Index: 877

Text #16

Max Range: 1.1648. Min Range: -1.1648

Max Act: 0.8270. Min Act: -0.0000

Data Index: 395312 (C4 (Web Text))

Max Activating Token Index: 60

Text #17

Max Range: 1.1648. Min Range: -1.1648

Max Act: 0.8282. Min Act: -0.0000

Data Index: 190590 (C4 (Web Text))

Max Activating Token Index: 440

Text #18

Max Range: 1.1648. Min Range: -1.1648

Max Act: 0.9874. Min Act: -0.0000

Data Index: 452206 (C4 (Web Text))

Max Activating Token Index: 212

Text #19

Max Range: 1.1648. Min Range: -1.1648

Max Act: 0.7923. Min Act: -0.0000

Data Index: 481860 (C4 (Web Text))

Max Activating Token Index: 24