Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1472 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2934. Min Range: -0.2934

Max Act: 0.2934. Min Act: -0.0001

Data Index: 875666 (C4 (Web Text))

Max Activating Token Index: 525

Text #1

Max Range: 0.2934. Min Range: -0.2934

Max Act: 0.2619. Min Act: -0.0001

Data Index: 1234814 (C4 (Web Text))

Max Activating Token Index: 936

Text #2

Max Range: 0.2934. Min Range: -0.2934

Max Act: 0.2471. Min Act: -0.0001

Data Index: 137008 (C4 (Web Text))

Max Activating Token Index: 251

Text #3

Max Range: 0.2934. Min Range: -0.2934

Max Act: 0.2074. Min Act: -0.0001

Data Index: 52153 (C4 (Web Text))

Max Activating Token Index: 708

Text #4

Max Range: 0.2934. Min Range: -0.2934

Max Act: 0.2105. Min Act: -0.0001

Data Index: 777047 (C4 (Web Text))

Max Activating Token Index: 582

Text #5

Max Range: 0.2934. Min Range: -0.2934

Max Act: 0.2039. Min Act: -0.0000

Data Index: 548369 (C4 (Web Text))

Max Activating Token Index: 884

Text #6

Max Range: 0.2934. Min Range: -0.2934

Max Act: 0.2138. Min Act: -0.0001

Data Index: 251446 (C4 (Web Text))

Max Activating Token Index: 876

Text #7

Max Range: 0.2934. Min Range: -0.2934

Max Act: 0.2008. Min Act: -0.0001

Data Index: 599680 (C4 (Web Text))

Max Activating Token Index: 27

Text #8

Max Range: 0.2934. Min Range: -0.2934

Max Act: 0.1914. Min Act: -0.0001

Data Index: 785066 (C4 (Web Text))

Max Activating Token Index: 503

Text #9

Max Range: 0.2934. Min Range: -0.2934

Max Act: 0.1979. Min Act: -0.0001

Data Index: 1188695 (C4 (Web Text))

Max Activating Token Index: 819

Text #10

Max Range: 0.2934. Min Range: -0.2934

Max Act: 0.1881. Min Act: -0.0001

Data Index: 984787 (C4 (Web Text))

Max Activating Token Index: 797

Text #11

Max Range: 0.2934. Min Range: -0.2934

Max Act: 0.1881. Min Act: -0.0001

Data Index: 1142950 (C4 (Web Text))

Max Activating Token Index: 1010

Text #12

Max Range: 0.2934. Min Range: -0.2934

Max Act: 0.1907. Min Act: -0.0001

Data Index: 256324 (C4 (Web Text))

Max Activating Token Index: 985

Text #13

Max Range: 0.2934. Min Range: -0.2934

Max Act: 0.1867. Min Act: 0.0000

Data Index: 45695 (C4 (Web Text))

Max Activating Token Index: 45

Text #14

Max Range: 0.2934. Min Range: -0.2934

Max Act: 0.1815. Min Act: -0.0001

Data Index: 498555 (C4 (Web Text))

Max Activating Token Index: 816

Text #15

Max Range: 0.2934. Min Range: -0.2934

Max Act: 0.1813. Min Act: -0.0001

Data Index: 804176 (C4 (Web Text))

Max Activating Token Index: 88

Text #16

Max Range: 0.2934. Min Range: -0.2934

Max Act: 0.1825. Min Act: -0.0001

Data Index: 59080 (C4 (Web Text))

Max Activating Token Index: 961

Text #17

Max Range: 0.2934. Min Range: -0.2934

Max Act: 0.1805. Min Act: -0.0001

Data Index: 248605 (C4 (Web Text))

Max Activating Token Index: 184

Text #18

Max Range: 0.2934. Min Range: -0.2934

Max Act: 0.1752. Min Act: -0.0001

Data Index: 1090929 (C4 (Web Text))

Max Activating Token Index: 185

Text #19

Max Range: 0.2934. Min Range: -0.2934

Max Act: 0.1784. Min Act: -0.0001

Data Index: 891592 (C4 (Web Text))

Max Activating Token Index: 599