Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 513 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0576. Min Range: -0.0576

Max Act: 0.0504. Min Act: -0.0003

Data Index: 571708 (C4 (Web Text))

Max Activating Token Index: 852

Text #1

Max Range: 0.0576. Min Range: -0.0576

Max Act: 0.0576. Min Act: -0.0003

Data Index: 312228 (C4 (Web Text))

Max Activating Token Index: 441

Text #2

Max Range: 0.0576. Min Range: -0.0576

Max Act: 0.0555. Min Act: -0.0003

Data Index: 37870 (C4 (Web Text))

Max Activating Token Index: 557

Text #3

Max Range: 0.0576. Min Range: -0.0576

Max Act: 0.0551. Min Act: -0.0003

Data Index: 756964 (C4 (Web Text))

Max Activating Token Index: 246

Text #4

Max Range: 0.0576. Min Range: -0.0576

Max Act: 0.0569. Min Act: -0.0003

Data Index: 529665 (C4 (Web Text))

Max Activating Token Index: 140

Text #5

Max Range: 0.0576. Min Range: -0.0576

Max Act: 0.0568. Min Act: -0.0003

Data Index: 910335 (C4 (Web Text))

Max Activating Token Index: 892

Text #6

Max Range: 0.0576. Min Range: -0.0576

Max Act: 0.0509. Min Act: -0.0003

Data Index: 83946 (C4 (Web Text))

Max Activating Token Index: 962

Text #7

Max Range: 0.0576. Min Range: -0.0576

Max Act: 0.0526. Min Act: -0.0003

Data Index: 938907 (C4 (Web Text))

Max Activating Token Index: 797

Text #8

Max Range: 0.0576. Min Range: -0.0576

Max Act: 0.0558. Min Act: -0.0003

Data Index: 1317394 (C4 (Web Text))

Max Activating Token Index: 607

Text #9

Max Range: 0.0576. Min Range: -0.0576

Max Act: 0.0509. Min Act: -0.0003

Data Index: 295647 (C4 (Web Text))

Max Activating Token Index: 564

Text #10

Max Range: 0.0576. Min Range: -0.0576

Max Act: 0.0523. Min Act: -0.0004

Data Index: 1120829 (C4 (Web Text))

Max Activating Token Index: 995

Text #11

Max Range: 0.0576. Min Range: -0.0576

Max Act: 0.0486. Min Act: -0.0003

Data Index: 402809 (C4 (Web Text))

Max Activating Token Index: 205

Text #12

Max Range: 0.0576. Min Range: -0.0576

Max Act: 0.0498. Min Act: -0.0003

Data Index: 96688 (C4 (Web Text))

Max Activating Token Index: 203

Text #13

Max Range: 0.0576. Min Range: -0.0576

Max Act: 0.0491. Min Act: -0.0003

Data Index: 435632 (C4 (Web Text))

Max Activating Token Index: 554

Text #14

Max Range: 0.0576. Min Range: -0.0576

Max Act: 0.0480. Min Act: -0.0003

Data Index: 1235481 (C4 (Web Text))

Max Activating Token Index: 823

Text #15

Max Range: 0.0576. Min Range: -0.0576

Max Act: 0.0507. Min Act: -0.0004

Data Index: 1230989 (C4 (Web Text))

Max Activating Token Index: 630

Text #16

Max Range: 0.0576. Min Range: -0.0576

Max Act: 0.0492. Min Act: -0.0003

Data Index: 967007 (C4 (Web Text))

Max Activating Token Index: 49

Text #17

Max Range: 0.0576. Min Range: -0.0576

Max Act: 0.0437. Min Act: -0.0003

Data Index: 232787 (C4 (Web Text))

Max Activating Token Index: 808

Text #18

Max Range: 0.0576. Min Range: -0.0576

Max Act: 0.0541. Min Act: -0.0003

Data Index: 63812 (C4 (Web Text))

Max Activating Token Index: 644

Text #19

Max Range: 0.0576. Min Range: -0.0576

Max Act: 0.0468. Min Act: -0.0003

Data Index: 1061112 (C4 (Web Text))

Max Activating Token Index: 31