Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3220 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.4984. Min Range: -0.4984

Max Act: 0.4984. Min Act: -0.0002

Data Index: 710786 (C4 (Web Text))

Max Activating Token Index: 206

Text #1

Max Range: 0.4984. Min Range: -0.4984

Max Act: 0.4735. Min Act: -0.0001

Data Index: 1303722 (C4 (Web Text))

Max Activating Token Index: 27

Text #2

Max Range: 0.4984. Min Range: -0.4984

Max Act: 0.4774. Min Act: -0.0001

Data Index: 524210 (C4 (Web Text))

Max Activating Token Index: 888

Text #3

Max Range: 0.4984. Min Range: -0.4984

Max Act: 0.4726. Min Act: -0.0001

Data Index: 513552 (C4 (Web Text))

Max Activating Token Index: 956

Text #4

Max Range: 0.4984. Min Range: -0.4984

Max Act: 0.4487. Min Act: -0.0002

Data Index: 1257035 (C4 (Web Text))

Max Activating Token Index: 624

Text #5

Max Range: 0.4984. Min Range: -0.4984

Max Act: 0.4839. Min Act: -0.0002

Data Index: 1062318 (C4 (Web Text))

Max Activating Token Index: 654

Text #6

Max Range: 0.4984. Min Range: -0.4984

Max Act: 0.4497. Min Act: -0.0001

Data Index: 1310434 (C4 (Web Text))

Max Activating Token Index: 872

Text #7

Max Range: 0.4984. Min Range: -0.4984

Max Act: 0.4284. Min Act: -0.0001

Data Index: 1269721 (C4 (Web Text))

Max Activating Token Index: 765

Text #8

Max Range: 0.4984. Min Range: -0.4984

Max Act: 0.4495. Min Act: -0.0002

Data Index: 1298302 (C4 (Web Text))

Max Activating Token Index: 156

Text #9

Max Range: 0.4984. Min Range: -0.4984

Max Act: 0.4302. Min Act: -0.0001

Data Index: 354272 (C4 (Web Text))

Max Activating Token Index: 342

Text #10

Max Range: 0.4984. Min Range: -0.4984

Max Act: 0.4353. Min Act: -0.0001

Data Index: 119845 (C4 (Web Text))

Max Activating Token Index: 740

Text #11

Max Range: 0.4984. Min Range: -0.4984

Max Act: 0.3769. Min Act: -0.0002

Data Index: 437146 (C4 (Web Text))

Max Activating Token Index: 958

Text #12

Max Range: 0.4984. Min Range: -0.4984

Max Act: 0.4289. Min Act: -0.0002

Data Index: 968130 (C4 (Web Text))

Max Activating Token Index: 7

Text #13

Max Range: 0.4984. Min Range: -0.4984

Max Act: 0.4026. Min Act: -0.0001

Data Index: 611053 (C4 (Web Text))

Max Activating Token Index: 846

Text #14

Max Range: 0.4984. Min Range: -0.4984

Max Act: 0.4250. Min Act: -0.0002

Data Index: 594407 (C4 (Web Text))

Max Activating Token Index: 820

Text #15

Max Range: 0.4984. Min Range: -0.4984

Max Act: 0.3816. Min Act: -0.0002

Data Index: 100355 (C4 (Web Text))

Max Activating Token Index: 559

Text #16

Max Range: 0.4984. Min Range: -0.4984

Max Act: 0.3964. Min Act: -0.0001

Data Index: 843806 (C4 (Web Text))

Max Activating Token Index: 1011

Text #17

Max Range: 0.4984. Min Range: -0.4984

Max Act: 0.3787. Min Act: -0.0001

Data Index: 1280321 (C4 (Web Text))

Max Activating Token Index: 881

Text #18

Max Range: 0.4984. Min Range: -0.4984

Max Act: 0.3918. Min Act: -0.0001

Data Index: 440678 (C4 (Web Text))

Max Activating Token Index: 870

Text #19

Max Range: 0.4984. Min Range: -0.4984

Max Act: 0.4008. Min Act: -0.0002

Data Index: 1196739 (C4 (Web Text))

Max Activating Token Index: 825