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

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

Neuron 4799 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0033. Min Range: -0.0033

Max Act: 0.0033. Min Act: -0.0002

Data Index: 1104230 (C4 (Web Text))

Max Activating Token Index: 922

Text #1

Max Range: 0.0033. Min Range: -0.0033

Max Act: 0.0032. Min Act: -0.0002

Data Index: 903100 (C4 (Web Text))

Max Activating Token Index: 964

Text #2

Max Range: 0.0033. Min Range: -0.0033

Max Act: 0.0031. Min Act: -0.0002

Data Index: 1070970 (C4 (Web Text))

Max Activating Token Index: 956

Text #3

Max Range: 0.0033. Min Range: -0.0033

Max Act: 0.0030. Min Act: -0.0002

Data Index: 506767 (C4 (Web Text))

Max Activating Token Index: 820

Text #4

Max Range: 0.0033. Min Range: -0.0033

Max Act: 0.0031. Min Act: -0.0002

Data Index: 961632 (C4 (Web Text))

Max Activating Token Index: 970

Text #5

Max Range: 0.0033. Min Range: -0.0033

Max Act: 0.0031. Min Act: -0.0002

Data Index: 879970 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.0033. Min Range: -0.0033

Max Act: 0.0030. Min Act: -0.0002

Data Index: 1255948 (C4 (Web Text))

Max Activating Token Index: 888

Text #7

Max Range: 0.0033. Min Range: -0.0033

Max Act: 0.0030. Min Act: -0.0002

Data Index: 220922 (C4 (Web Text))

Max Activating Token Index: 738

Text #8

Max Range: 0.0033. Min Range: -0.0033

Max Act: 0.0030. Min Act: -0.0002

Data Index: 95459 (C4 (Web Text))

Max Activating Token Index: 800

Text #9

Max Range: 0.0033. Min Range: -0.0033

Max Act: 0.0030. Min Act: -0.0002

Data Index: 528283 (C4 (Web Text))

Max Activating Token Index: 886

Text #10

Max Range: 0.0033. Min Range: -0.0033

Max Act: 0.0030. Min Act: -0.0002

Data Index: 1059975 (C4 (Web Text))

Max Activating Token Index: 975

Text #11

Max Range: 0.0033. Min Range: -0.0033

Max Act: 0.0030. Min Act: -0.0002

Data Index: 444232 (C4 (Web Text))

Max Activating Token Index: 952

Text #12

Max Range: 0.0033. Min Range: -0.0033

Max Act: 0.0030. Min Act: -0.0002

Data Index: 422691 (C4 (Web Text))

Max Activating Token Index: 943

Text #13

Max Range: 0.0033. Min Range: -0.0033

Max Act: 0.0030. Min Act: -0.0002

Data Index: 143197 (C4 (Web Text))

Max Activating Token Index: 233

Text #14

Max Range: 0.0033. Min Range: -0.0033

Max Act: 0.0029. Min Act: -0.0002

Data Index: 1000169 (C4 (Web Text))

Max Activating Token Index: 864

Text #15

Max Range: 0.0033. Min Range: -0.0033

Max Act: 0.0029. Min Act: -0.0002

Data Index: 1070105 (C4 (Web Text))

Max Activating Token Index: 917

Text #16

Max Range: 0.0033. Min Range: -0.0033

Max Act: 0.0030. Min Act: -0.0002

Data Index: 104164 (C4 (Web Text))

Max Activating Token Index: 995

Text #17

Max Range: 0.0033. Min Range: -0.0033

Max Act: 0.0029. Min Act: -0.0002

Data Index: 928230 (C4 (Web Text))

Max Activating Token Index: 963

Text #18

Max Range: 0.0033. Min Range: -0.0033

Max Act: 0.0029. Min Act: -0.0002

Data Index: 421354 (C4 (Web Text))

Max Activating Token Index: 982

Text #19

Max Range: 0.0033. Min Range: -0.0033

Max Act: 0.0029. Min Act: -0.0002

Data Index: 868066 (C4 (Web Text))

Max Activating Token Index: 971