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

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

Neuron 2070 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: 0.2181. Min Range: -0.2181

Max Act: 0.2114. Min Act: -0.0001

Data Index: 487444 (C4 (Web Text))

Max Activating Token Index: 870

Text #1

Max Range: 0.2181. Min Range: -0.2181

Max Act: 0.2045. Min Act: -0.0001

Data Index: 24378 (C4 (Web Text))

Max Activating Token Index: 842

Text #2

Max Range: 0.2181. Min Range: -0.2181

Max Act: 0.2133. Min Act: -0.0001

Data Index: 1151264 (C4 (Web Text))

Max Activating Token Index: 925

Text #3

Max Range: 0.2181. Min Range: -0.2181

Max Act: 0.2181. Min Act: -0.0001

Data Index: 415852 (C4 (Web Text))

Max Activating Token Index: 697

Text #4

Max Range: 0.2181. Min Range: -0.2181

Max Act: 0.2057. Min Act: -0.0001

Data Index: 330196 (C4 (Web Text))

Max Activating Token Index: 865

Text #5

Max Range: 0.2181. Min Range: -0.2181

Max Act: 0.1967. Min Act: -0.0001

Data Index: 15461 (C4 (Web Text))

Max Activating Token Index: 447

Text #6

Max Range: 0.2181. Min Range: -0.2181

Max Act: 0.1981. Min Act: -0.0001

Data Index: 1011843 (C4 (Web Text))

Max Activating Token Index: 909

Text #7

Max Range: 0.2181. Min Range: -0.2181

Max Act: 0.2042. Min Act: -0.0001

Data Index: 377206 (C4 (Web Text))

Max Activating Token Index: 74

Text #8

Max Range: 0.2181. Min Range: -0.2181

Max Act: 0.1931. Min Act: -0.0001

Data Index: 1286327 (C4 (Web Text))

Max Activating Token Index: 151

Text #9

Max Range: 0.2181. Min Range: -0.2181

Max Act: 0.1855. Min Act: -0.0001

Data Index: 211790 (C4 (Web Text))

Max Activating Token Index: 953

Text #10

Max Range: 0.2181. Min Range: -0.2181

Max Act: 0.1956. Min Act: -0.0001

Data Index: 1120917 (C4 (Web Text))

Max Activating Token Index: 953

Text #11

Max Range: 0.2181. Min Range: -0.2181

Max Act: 0.1855. Min Act: -0.0001

Data Index: 824634 (C4 (Web Text))

Max Activating Token Index: 961

Text #12

Max Range: 0.2181. Min Range: -0.2181

Max Act: 0.1778. Min Act: -0.0001

Data Index: 1094190 (C4 (Web Text))

Max Activating Token Index: 99

Text #13

Max Range: 0.2181. Min Range: -0.2181

Max Act: 0.1824. Min Act: -0.0001

Data Index: 266808 (C4 (Web Text))

Max Activating Token Index: 837

Text #14

Max Range: 0.2181. Min Range: -0.2181

Max Act: 0.1869. Min Act: -0.0001

Data Index: 1182357 (C4 (Web Text))

Max Activating Token Index: 1003

Text #15

Max Range: 0.2181. Min Range: -0.2181

Max Act: 0.1795. Min Act: -0.0001

Data Index: 68607 (C4 (Web Text))

Max Activating Token Index: 724

Text #16

Max Range: 0.2181. Min Range: -0.2181

Max Act: 0.1732. Min Act: -0.0001

Data Index: 259400 (C4 (Web Text))

Max Activating Token Index: 93

Text #17

Max Range: 0.2181. Min Range: -0.2181

Max Act: 0.1788. Min Act: -0.0001

Data Index: 1251125 (C4 (Web Text))

Max Activating Token Index: 973

Text #18

Max Range: 0.2181. Min Range: -0.2181

Max Act: 0.1779. Min Act: -0.0001

Data Index: 603797 (C4 (Web Text))

Max Activating Token Index: 876

Text #19

Max Range: 0.2181. Min Range: -0.2181

Max Act: 0.1733. Min Act: -0.0001

Data Index: 773688 (C4 (Web Text))

Max Activating Token Index: 430