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

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

Neuron 420 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0965. Min Range: -2.0965

Max Act: 2.0965. Min Act: -0.0000

Data Index: 372888 (C4 (Web Text))

Max Activating Token Index: 262

Text #1

Max Range: 2.0965. Min Range: -2.0965

Max Act: 2.0474. Min Act: -0.0000

Data Index: 781011 (C4 (Web Text))

Max Activating Token Index: 764

Text #2

Max Range: 2.0965. Min Range: -2.0965

Max Act: 1.9274. Min Act: -0.0000

Data Index: 649771 (C4 (Web Text))

Max Activating Token Index: 960

Text #3

Max Range: 2.0965. Min Range: -2.0965

Max Act: 1.9274. Min Act: -0.0000

Data Index: 315751 (C4 (Web Text))

Max Activating Token Index: 291

Text #4

Max Range: 2.0965. Min Range: -2.0965

Max Act: 1.9112. Min Act: -0.0000

Data Index: 83026 (C4 (Web Text))

Max Activating Token Index: 38

Text #5

Max Range: 2.0965. Min Range: -2.0965

Max Act: 1.8722. Min Act: -0.0000

Data Index: 962750 (C4 (Web Text))

Max Activating Token Index: 387

Text #6

Max Range: 2.0965. Min Range: -2.0965

Max Act: 1.9711. Min Act: -0.0000

Data Index: 1053187 (C4 (Web Text))

Max Activating Token Index: 15

Text #7

Max Range: 2.0965. Min Range: -2.0965

Max Act: 1.9346. Min Act: -0.0000

Data Index: 884372 (C4 (Web Text))

Max Activating Token Index: 907

Text #8

Max Range: 2.0965. Min Range: -2.0965

Max Act: 1.6724. Min Act: -0.0000

Data Index: 1159117 (C4 (Web Text))

Max Activating Token Index: 223

Text #9

Max Range: 2.0965. Min Range: -2.0965

Max Act: 1.7338. Min Act: -0.0000

Data Index: 1330661 (C4 (Web Text))

Max Activating Token Index: 564

Text #10

Max Range: 2.0965. Min Range: -2.0965

Max Act: 1.7187. Min Act: -0.0000

Data Index: 1212082 (C4 (Web Text))

Max Activating Token Index: 1007

Text #11

Max Range: 2.0965. Min Range: -2.0965

Max Act: 1.7161. Min Act: -0.0000

Data Index: 295368 (C4 (Web Text))

Max Activating Token Index: 678

Text #12

Max Range: 2.0965. Min Range: -2.0965

Max Act: 1.6975. Min Act: -0.0000

Data Index: 636749 (C4 (Web Text))

Max Activating Token Index: 978

Text #13

Max Range: 2.0965. Min Range: -2.0965

Max Act: 1.6845. Min Act: -0.0000

Data Index: 679459 (C4 (Web Text))

Max Activating Token Index: 770

Text #14

Max Range: 2.0965. Min Range: -2.0965

Max Act: 1.6977. Min Act: -0.0000

Data Index: 712798 (C4 (Web Text))

Max Activating Token Index: 942

Text #15

Max Range: 2.0965. Min Range: -2.0965

Max Act: 1.6723. Min Act: -0.0000

Data Index: 553934 (C4 (Web Text))

Max Activating Token Index: 415

Text #16

Max Range: 2.0965. Min Range: -2.0965

Max Act: 1.5763. Min Act: -0.0000

Data Index: 1333198 (C4 (Web Text))

Max Activating Token Index: 752

Text #17

Max Range: 2.0965. Min Range: -2.0965

Max Act: 1.6572. Min Act: -0.0000

Data Index: 1277898 (C4 (Web Text))

Max Activating Token Index: 860

Text #18

Max Range: 2.0965. Min Range: -2.0965

Max Act: 1.6478. Min Act: -0.0000

Data Index: 265945 (C4 (Web Text))

Max Activating Token Index: 48

Text #19

Max Range: 2.0965. Min Range: -2.0965

Max Act: 1.6220. Min Act: -0.0000

Data Index: 458773 (C4 (Web Text))

Max Activating Token Index: 755