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

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

Neuron 4380 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2987. Min Range: -0.2987

Max Act: 0.2985. Min Act: -0.0000

Data Index: 723663 (C4 (Web Text))

Max Activating Token Index: 200

Text #1

Max Range: 0.2987. Min Range: -0.2987

Max Act: 0.2987. Min Act: -0.0000

Data Index: 431572 (C4 (Web Text))

Max Activating Token Index: 435

Text #2

Max Range: 0.2987. Min Range: -0.2987

Max Act: 0.2676. Min Act: -0.0000

Data Index: 445577 (C4 (Web Text))

Max Activating Token Index: 820

Text #3

Max Range: 0.2987. Min Range: -0.2987

Max Act: 0.2603. Min Act: -0.0000

Data Index: 1238324 (C4 (Web Text))

Max Activating Token Index: 653

Text #4

Max Range: 0.2987. Min Range: -0.2987

Max Act: 0.2622. Min Act: -0.0000

Data Index: 1174736 (C4 (Web Text))

Max Activating Token Index: 118

Text #5

Max Range: 0.2987. Min Range: -0.2987

Max Act: 0.2697. Min Act: -0.0000

Data Index: 135974 (C4 (Web Text))

Max Activating Token Index: 274

Text #6

Max Range: 0.2987. Min Range: -0.2987

Max Act: 0.2392. Min Act: -0.0000

Data Index: 493813 (C4 (Web Text))

Max Activating Token Index: 407

Text #7

Max Range: 0.2987. Min Range: -0.2987

Max Act: 0.2525. Min Act: -0.0000

Data Index: 325739 (C4 (Web Text))

Max Activating Token Index: 643

Text #8

Max Range: 0.2987. Min Range: -0.2987

Max Act: 0.2303. Min Act: -0.0000

Data Index: 1271011 (C4 (Web Text))

Max Activating Token Index: 689

Text #9

Max Range: 0.2987. Min Range: -0.2987

Max Act: 0.2328. Min Act: -0.0000

Data Index: 1198029 (C4 (Web Text))

Max Activating Token Index: 554

Text #10

Max Range: 0.2987. Min Range: -0.2987

Max Act: 0.2110. Min Act: -0.0000

Data Index: 884514 (C4 (Web Text))

Max Activating Token Index: 613

Text #11

Max Range: 0.2987. Min Range: -0.2987

Max Act: 0.2112. Min Act: -0.0000

Data Index: 1176650 (C4 (Web Text))

Max Activating Token Index: 70

Text #12

Max Range: 0.2987. Min Range: -0.2987

Max Act: 0.2069. Min Act: -0.0000

Data Index: 639882 (C4 (Web Text))

Max Activating Token Index: 768

Text #13

Max Range: 0.2987. Min Range: -0.2987

Max Act: 0.1916. Min Act: -0.0000

Data Index: 1198913 (C4 (Web Text))

Max Activating Token Index: 295

Text #14

Max Range: 0.2987. Min Range: -0.2987

Max Act: 0.1939. Min Act: -0.0000

Data Index: 989233 (C4 (Web Text))

Max Activating Token Index: 904

Text #15

Max Range: 0.2987. Min Range: -0.2987

Max Act: 0.2024. Min Act: -0.0000

Data Index: 646879 (C4 (Web Text))

Max Activating Token Index: 108

Text #16

Max Range: 0.2987. Min Range: -0.2987

Max Act: 0.2115. Min Act: -0.0000

Data Index: 657665 (C4 (Web Text))

Max Activating Token Index: 95

Text #17

Max Range: 0.2987. Min Range: -0.2987

Max Act: 0.2106. Min Act: -0.0000

Data Index: 892183 (C4 (Web Text))

Max Activating Token Index: 337

Text #18

Max Range: 0.2987. Min Range: -0.2987

Max Act: 0.2122. Min Act: -0.0000

Data Index: 993199 (C4 (Web Text))

Max Activating Token Index: 695

Text #19

Max Range: 0.2987. Min Range: -0.2987

Max Act: 0.2171. Min Act: -0.0000

Data Index: 863510 (C4 (Web Text))

Max Activating Token Index: 284