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

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

Neuron 250 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.0734. Min Range: -1.0734

Max Act: 1.0734. Min Act: -0.0000

Data Index: 1109065 (C4 (Web Text))

Max Activating Token Index: 201

Text #1

Max Range: 1.0734. Min Range: -1.0734

Max Act: 1.0022. Min Act: -0.0000

Data Index: 573767 (C4 (Web Text))

Max Activating Token Index: 75

Text #2

Max Range: 1.0734. Min Range: -1.0734

Max Act: 0.9718. Min Act: -0.0000

Data Index: 744514 (C4 (Web Text))

Max Activating Token Index: 150

Text #3

Max Range: 1.0734. Min Range: -1.0734

Max Act: 0.9140. Min Act: -0.0000

Data Index: 69640 (C4 (Web Text))

Max Activating Token Index: 524

Text #4

Max Range: 1.0734. Min Range: -1.0734

Max Act: 0.9067. Min Act: -0.0000

Data Index: 1057266 (C4 (Web Text))

Max Activating Token Index: 185

Text #5

Max Range: 1.0734. Min Range: -1.0734

Max Act: 0.8717. Min Act: -0.0000

Data Index: 62583 (C4 (Web Text))

Max Activating Token Index: 491

Text #6

Max Range: 1.0734. Min Range: -1.0734

Max Act: 0.8724. Min Act: -0.0000

Data Index: 1332682 (C4 (Web Text))

Max Activating Token Index: 198

Text #7

Max Range: 1.0734. Min Range: -1.0734

Max Act: 0.9147. Min Act: -0.0000

Data Index: 73490 (C4 (Web Text))

Max Activating Token Index: 701

Text #8

Max Range: 1.0734. Min Range: -1.0734

Max Act: 0.9070. Min Act: -0.0000

Data Index: 1125280 (C4 (Web Text))

Max Activating Token Index: 191

Text #9

Max Range: 1.0734. Min Range: -1.0734

Max Act: 0.8705. Min Act: -0.0000

Data Index: 748608 (C4 (Web Text))

Max Activating Token Index: 747

Text #10

Max Range: 1.0734. Min Range: -1.0734

Max Act: 0.8885. Min Act: -0.0000

Data Index: 1081423 (C4 (Web Text))

Max Activating Token Index: 835

Text #11

Max Range: 1.0734. Min Range: -1.0734

Max Act: 0.7916. Min Act: -0.0000

Data Index: 1284417 (C4 (Web Text))

Max Activating Token Index: 736

Text #12

Max Range: 1.0734. Min Range: -1.0734

Max Act: 0.7828. Min Act: -0.0000

Data Index: 999232 (C4 (Web Text))

Max Activating Token Index: 158

Text #13

Max Range: 1.0734. Min Range: -1.0734

Max Act: 0.7732. Min Act: -0.0000

Data Index: 1185855 (C4 (Web Text))

Max Activating Token Index: 874

Text #14

Max Range: 1.0734. Min Range: -1.0734

Max Act: 0.6974. Min Act: -0.0000

Data Index: 19657 (C4 (Web Text))

Max Activating Token Index: 591

Text #15

Max Range: 1.0734. Min Range: -1.0734

Max Act: 0.7661. Min Act: -0.0000

Data Index: 166793 (C4 (Web Text))

Max Activating Token Index: 502

Text #16

Max Range: 1.0734. Min Range: -1.0734

Max Act: 0.7130. Min Act: -0.0000

Data Index: 288042 (C4 (Web Text))

Max Activating Token Index: 710

Text #17

Max Range: 1.0734. Min Range: -1.0734

Max Act: 0.7258. Min Act: -0.0000

Data Index: 35027 (C4 (Web Text))

Max Activating Token Index: 278

Text #18

Max Range: 1.0734. Min Range: -1.0734

Max Act: 0.7154. Min Act: -0.0000

Data Index: 934504 (C4 (Web Text))

Max Activating Token Index: 216

Text #19

Max Range: 1.0734. Min Range: -1.0734

Max Act: 0.7209. Min Act: -0.0000

Data Index: 748982 (C4 (Web Text))

Max Activating Token Index: 364