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

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

Neuron 988 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: 0.1057. Min Range: -0.1057

Max Act: 0.1057. Min Act: -0.0001

Data Index: 148843 (C4 (Web Text))

Max Activating Token Index: 879

Text #1

Max Range: 0.1057. Min Range: -0.1057

Max Act: 0.1019. Min Act: -0.0002

Data Index: 74499 (C4 (Web Text))

Max Activating Token Index: 989

Text #2

Max Range: 0.1057. Min Range: -0.1057

Max Act: 0.0988. Min Act: -0.0001

Data Index: 317385 (C4 (Web Text))

Max Activating Token Index: 13

Text #3

Max Range: 0.1057. Min Range: -0.1057

Max Act: 0.1002. Min Act: -0.0002

Data Index: 626676 (C4 (Web Text))

Max Activating Token Index: 737

Text #4

Max Range: 0.1057. Min Range: -0.1057

Max Act: 0.0947. Min Act: -0.0001

Data Index: 1562272 (Python Code)

Max Activating Token Index: 995

Text #5

Max Range: 0.1057. Min Range: -0.1057

Max Act: 0.0919. Min Act: -0.0001

Data Index: 1307842 (C4 (Web Text))

Max Activating Token Index: 741

Text #6

Max Range: 0.1057. Min Range: -0.1057

Max Act: 0.0910. Min Act: -0.0001

Data Index: 352879 (C4 (Web Text))

Max Activating Token Index: 974

Text #7

Max Range: 0.1057. Min Range: -0.1057

Max Act: 0.0835. Min Act: -0.0002

Data Index: 1000733 (C4 (Web Text))

Max Activating Token Index: 982

Text #8

Max Range: 0.1057. Min Range: -0.1057

Max Act: 0.0824. Min Act: -0.0002

Data Index: 1261620 (C4 (Web Text))

Max Activating Token Index: 972

Text #9

Max Range: 0.1057. Min Range: -0.1057

Max Act: 0.0820. Min Act: -0.0002

Data Index: 1327667 (C4 (Web Text))

Max Activating Token Index: 540

Text #10

Max Range: 0.1057. Min Range: -0.1057

Max Act: 0.0869. Min Act: -0.0001

Data Index: 1609131 (Python Code)

Max Activating Token Index: 948

Text #11

Max Range: 0.1057. Min Range: -0.1057

Max Act: 0.0743. Min Act: -0.0001

Data Index: 913881 (C4 (Web Text))

Max Activating Token Index: 407

Text #12

Max Range: 0.1057. Min Range: -0.1057

Max Act: 0.0761. Min Act: -0.0001

Data Index: 902860 (C4 (Web Text))

Max Activating Token Index: 527

Text #13

Max Range: 0.1057. Min Range: -0.1057

Max Act: 0.0722. Min Act: -0.0002

Data Index: 1106294 (C4 (Web Text))

Max Activating Token Index: 737

Text #14

Max Range: 0.1057. Min Range: -0.1057

Max Act: 0.0788. Min Act: -0.0001

Data Index: 5588 (C4 (Web Text))

Max Activating Token Index: 813

Text #15

Max Range: 0.1057. Min Range: -0.1057

Max Act: 0.0784. Min Act: -0.0002

Data Index: 1331873 (C4 (Web Text))

Max Activating Token Index: 961

Text #16

Max Range: 0.1057. Min Range: -0.1057

Max Act: 0.0750. Min Act: -0.0001

Data Index: 1316935 (C4 (Web Text))

Max Activating Token Index: 990

Text #17

Max Range: 0.1057. Min Range: -0.1057

Max Act: 0.0721. Min Act: -0.0001

Data Index: 1517379 (Python Code)

Max Activating Token Index: 928

Text #18

Max Range: 0.1057. Min Range: -0.1057

Max Act: 0.0775. Min Act: -0.0002

Data Index: 963521 (C4 (Web Text))

Max Activating Token Index: 437

Text #19

Max Range: 0.1057. Min Range: -0.1057

Max Act: 0.0778. Min Act: -0.0001

Data Index: 80754 (C4 (Web Text))

Max Activating Token Index: 964