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

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

Neuron 2124 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2110. Min Range: -1.2110

Max Act: 1.2110. Min Act: -0.0001

Data Index: 311476 (C4 (Web Text))

Max Activating Token Index: 467

Text #1

Max Range: 1.2110. Min Range: -1.2110

Max Act: 1.0376. Min Act: -0.0001

Data Index: 497516 (C4 (Web Text))

Max Activating Token Index: 456

Text #2

Max Range: 1.2110. Min Range: -1.2110

Max Act: 0.9693. Min Act: -0.0001

Data Index: 912414 (C4 (Web Text))

Max Activating Token Index: 528

Text #3

Max Range: 1.2110. Min Range: -1.2110

Max Act: 1.0265. Min Act: -0.0001

Data Index: 1128729 (C4 (Web Text))

Max Activating Token Index: 535

Text #4

Max Range: 1.2110. Min Range: -1.2110

Max Act: 1.0088. Min Act: -0.0001

Data Index: 1067196 (C4 (Web Text))

Max Activating Token Index: 1004

Text #5

Max Range: 1.2110. Min Range: -1.2110

Max Act: 0.9959. Min Act: -0.0001

Data Index: 1116467 (C4 (Web Text))

Max Activating Token Index: 485

Text #6

Max Range: 1.2110. Min Range: -1.2110

Max Act: 0.8725. Min Act: -0.0001

Data Index: 568934 (C4 (Web Text))

Max Activating Token Index: 829

Text #7

Max Range: 1.2110. Min Range: -1.2110

Max Act: 1.0278. Min Act: -0.0001

Data Index: 1174237 (C4 (Web Text))

Max Activating Token Index: 986

Text #8

Max Range: 1.2110. Min Range: -1.2110

Max Act: 0.9950. Min Act: -0.0001

Data Index: 212108 (C4 (Web Text))

Max Activating Token Index: 354

Text #9

Max Range: 1.2110. Min Range: -1.2110

Max Act: 0.8713. Min Act: -0.0001

Data Index: 546441 (C4 (Web Text))

Max Activating Token Index: 641

Text #10

Max Range: 1.2110. Min Range: -1.2110

Max Act: 0.9939. Min Act: -0.0001

Data Index: 615115 (C4 (Web Text))

Max Activating Token Index: 359

Text #11

Max Range: 1.2110. Min Range: -1.2110

Max Act: 1.0581. Min Act: -0.0001

Data Index: 118162 (C4 (Web Text))

Max Activating Token Index: 845

Text #12

Max Range: 1.2110. Min Range: -1.2110

Max Act: 0.9637. Min Act: -0.0001

Data Index: 778089 (C4 (Web Text))

Max Activating Token Index: 452

Text #13

Max Range: 1.2110. Min Range: -1.2110

Max Act: 0.9370. Min Act: -0.0001

Data Index: 1159818 (C4 (Web Text))

Max Activating Token Index: 211

Text #14

Max Range: 1.2110. Min Range: -1.2110

Max Act: 0.9794. Min Act: -0.0001

Data Index: 488683 (C4 (Web Text))

Max Activating Token Index: 978

Text #15

Max Range: 1.2110. Min Range: -1.2110

Max Act: 1.0016. Min Act: -0.0001

Data Index: 124117 (C4 (Web Text))

Max Activating Token Index: 889

Text #16

Max Range: 1.2110. Min Range: -1.2110

Max Act: 0.9826. Min Act: -0.0001

Data Index: 2090 (C4 (Web Text))

Max Activating Token Index: 477

Text #17

Max Range: 1.2110. Min Range: -1.2110

Max Act: 0.8632. Min Act: -0.0001

Data Index: 986757 (C4 (Web Text))

Max Activating Token Index: 518

Text #18

Max Range: 1.2110. Min Range: -1.2110

Max Act: 0.9252. Min Act: -0.0001

Data Index: 1056971 (C4 (Web Text))

Max Activating Token Index: 1017

Text #19

Max Range: 1.2110. Min Range: -1.2110

Max Act: 0.8806. Min Act: -0.0001

Data Index: 131852 (C4 (Web Text))

Max Activating Token Index: 493