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

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

Neuron 2604 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2045. Min Range: -0.2045

Max Act: 0.1776. Min Act: -0.0001

Data Index: 1005806 (C4 (Web Text))

Max Activating Token Index: 334

Text #1

Max Range: 0.2045. Min Range: -0.2045

Max Act: 0.1939. Min Act: -0.0001

Data Index: 405429 (C4 (Web Text))

Max Activating Token Index: 283

Text #2

Max Range: 0.2045. Min Range: -0.2045

Max Act: 0.1905. Min Act: -0.0001

Data Index: 195130 (C4 (Web Text))

Max Activating Token Index: 848

Text #3

Max Range: 0.2045. Min Range: -0.2045

Max Act: 0.2045. Min Act: -0.0001

Data Index: 1328562 (C4 (Web Text))

Max Activating Token Index: 774

Text #4

Max Range: 0.2045. Min Range: -0.2045

Max Act: 0.1931. Min Act: -0.0001

Data Index: 778821 (C4 (Web Text))

Max Activating Token Index: 175

Text #5

Max Range: 0.2045. Min Range: -0.2045

Max Act: 0.1924. Min Act: -0.0001

Data Index: 95159 (C4 (Web Text))

Max Activating Token Index: 227

Text #6

Max Range: 0.2045. Min Range: -0.2045

Max Act: 0.1861. Min Act: -0.0001

Data Index: 1169493 (C4 (Web Text))

Max Activating Token Index: 209

Text #7

Max Range: 0.2045. Min Range: -0.2045

Max Act: 0.1813. Min Act: -0.0001

Data Index: 1033973 (C4 (Web Text))

Max Activating Token Index: 42

Text #8

Max Range: 0.2045. Min Range: -0.2045

Max Act: 0.1939. Min Act: -0.0001

Data Index: 165675 (C4 (Web Text))

Max Activating Token Index: 46

Text #9

Max Range: 0.2045. Min Range: -0.2045

Max Act: 0.1869. Min Act: -0.0001

Data Index: 1155052 (C4 (Web Text))

Max Activating Token Index: 397

Text #10

Max Range: 0.2045. Min Range: -0.2045

Max Act: 0.1785. Min Act: -0.0001

Data Index: 1114251 (C4 (Web Text))

Max Activating Token Index: 228

Text #11

Max Range: 0.2045. Min Range: -0.2045

Max Act: 0.1892. Min Act: -0.0001

Data Index: 1251925 (C4 (Web Text))

Max Activating Token Index: 260

Text #12

Max Range: 0.2045. Min Range: -0.2045

Max Act: 0.1813. Min Act: -0.0001

Data Index: 298430 (C4 (Web Text))

Max Activating Token Index: 793

Text #13

Max Range: 0.2045. Min Range: -0.2045

Max Act: 0.1683. Min Act: -0.0001

Data Index: 950499 (C4 (Web Text))

Max Activating Token Index: 247

Text #14

Max Range: 0.2045. Min Range: -0.2045

Max Act: 0.1875. Min Act: -0.0001

Data Index: 1034958 (C4 (Web Text))

Max Activating Token Index: 912

Text #15

Max Range: 0.2045. Min Range: -0.2045

Max Act: 0.1689. Min Act: -0.0001

Data Index: 634345 (C4 (Web Text))

Max Activating Token Index: 500

Text #16

Max Range: 0.2045. Min Range: -0.2045

Max Act: 0.1730. Min Act: -0.0001

Data Index: 633078 (C4 (Web Text))

Max Activating Token Index: 572

Text #17

Max Range: 0.2045. Min Range: -0.2045

Max Act: 0.1611. Min Act: -0.0001

Data Index: 194610 (C4 (Web Text))

Max Activating Token Index: 1019

Text #18

Max Range: 0.2045. Min Range: -0.2045

Max Act: 0.1765. Min Act: -0.0001

Data Index: 180659 (C4 (Web Text))

Max Activating Token Index: 401

Text #19

Max Range: 0.2045. Min Range: -0.2045

Max Act: 0.1764. Min Act: -0.0001

Data Index: 1271124 (C4 (Web Text))

Max Activating Token Index: 44