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

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

Neuron 5009 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6324. Min Range: -0.6324

Max Act: 0.6324. Min Act: -0.0000

Data Index: 299727 (C4 (Web Text))

Max Activating Token Index: 501

Text #1

Max Range: 0.6324. Min Range: -0.6324

Max Act: 0.5792. Min Act: -0.0000

Data Index: 732087 (C4 (Web Text))

Max Activating Token Index: 300

Text #2

Max Range: 0.6324. Min Range: -0.6324

Max Act: 0.5067. Min Act: -0.0000

Data Index: 1320827 (C4 (Web Text))

Max Activating Token Index: 744

Text #3

Max Range: 0.6324. Min Range: -0.6324

Max Act: 0.5390. Min Act: -0.0000

Data Index: 280203 (C4 (Web Text))

Max Activating Token Index: 525

Text #4

Max Range: 0.6324. Min Range: -0.6324

Max Act: 0.5240. Min Act: -0.0000

Data Index: 1257889 (C4 (Web Text))

Max Activating Token Index: 576

Text #5

Max Range: 0.6324. Min Range: -0.6324

Max Act: 0.5392. Min Act: -0.0000

Data Index: 1321402 (C4 (Web Text))

Max Activating Token Index: 229

Text #6

Max Range: 0.6324. Min Range: -0.6324

Max Act: 0.5129. Min Act: -0.0000

Data Index: 1099801 (C4 (Web Text))

Max Activating Token Index: 128

Text #7

Max Range: 0.6324. Min Range: -0.6324

Max Act: 0.4759. Min Act: -0.0000

Data Index: 1351250 (C4 (Web Text))

Max Activating Token Index: 764

Text #8

Max Range: 0.6324. Min Range: -0.6324

Max Act: 0.5287. Min Act: -0.0000

Data Index: 1123939 (C4 (Web Text))

Max Activating Token Index: 46

Text #9

Max Range: 0.6324. Min Range: -0.6324

Max Act: 0.4878. Min Act: -0.0000

Data Index: 375994 (C4 (Web Text))

Max Activating Token Index: 574

Text #10

Max Range: 0.6324. Min Range: -0.6324

Max Act: 0.4483. Min Act: -0.0000

Data Index: 885439 (C4 (Web Text))

Max Activating Token Index: 517

Text #11

Max Range: 0.6324. Min Range: -0.6324

Max Act: 0.4633. Min Act: -0.0000

Data Index: 610303 (C4 (Web Text))

Max Activating Token Index: 499

Text #12

Max Range: 0.6324. Min Range: -0.6324

Max Act: 0.4845. Min Act: -0.0000

Data Index: 560882 (C4 (Web Text))

Max Activating Token Index: 857

Text #13

Max Range: 0.6324. Min Range: -0.6324

Max Act: 0.4170. Min Act: -0.0000

Data Index: 913873 (C4 (Web Text))

Max Activating Token Index: 317

Text #14

Max Range: 0.6324. Min Range: -0.6324

Max Act: 0.4641. Min Act: -0.0000

Data Index: 739734 (C4 (Web Text))

Max Activating Token Index: 236

Text #15

Max Range: 0.6324. Min Range: -0.6324

Max Act: 0.4559. Min Act: -0.0000

Data Index: 172721 (C4 (Web Text))

Max Activating Token Index: 760

Text #16

Max Range: 0.6324. Min Range: -0.6324

Max Act: 0.4398. Min Act: -0.0000

Data Index: 339004 (C4 (Web Text))

Max Activating Token Index: 864

Text #17

Max Range: 0.6324. Min Range: -0.6324

Max Act: 0.4287. Min Act: -0.0000

Data Index: 798433 (C4 (Web Text))

Max Activating Token Index: 911

Text #18

Max Range: 0.6324. Min Range: -0.6324

Max Act: 0.4186. Min Act: -0.0000

Data Index: 936303 (C4 (Web Text))

Max Activating Token Index: 980

Text #19

Max Range: 0.6324. Min Range: -0.6324

Max Act: 0.4194. Min Act: -0.0000

Data Index: 1053854 (C4 (Web Text))

Max Activating Token Index: 178