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

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

Neuron 380 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0545. Min Act: -0.0003

Data Index: 166651 (C4 (Web Text))

Max Activating Token Index: 983

Text #1

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0539. Min Act: -0.0003

Data Index: 3969 (C4 (Web Text))

Max Activating Token Index: 698

Text #2

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0477. Min Act: -0.0003

Data Index: 767701 (C4 (Web Text))

Max Activating Token Index: 764

Text #3

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0516. Min Act: -0.0003

Data Index: 239647 (C4 (Web Text))

Max Activating Token Index: 105

Text #4

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0498. Min Act: -0.0003

Data Index: 1166588 (C4 (Web Text))

Max Activating Token Index: 45

Text #5

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0466. Min Act: -0.0003

Data Index: 1244180 (C4 (Web Text))

Max Activating Token Index: 56

Text #6

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0452. Min Act: -0.0003

Data Index: 896895 (C4 (Web Text))

Max Activating Token Index: 366

Text #7

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0494. Min Act: -0.0003

Data Index: 1022784 (C4 (Web Text))

Max Activating Token Index: 888

Text #8

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0483. Min Act: -0.0003

Data Index: 1173449 (C4 (Web Text))

Max Activating Token Index: 870

Text #9

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0425. Min Act: -0.0003

Data Index: 378953 (C4 (Web Text))

Max Activating Token Index: 919

Text #10

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0497. Min Act: -0.0003

Data Index: 876062 (C4 (Web Text))

Max Activating Token Index: 887

Text #11

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0449. Min Act: -0.0003

Data Index: 1357099 (C4 (Web Text))

Max Activating Token Index: 892

Text #12

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0440. Min Act: -0.0003

Data Index: 187801 (C4 (Web Text))

Max Activating Token Index: 978

Text #13

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0437. Min Act: -0.0003

Data Index: 1319792 (C4 (Web Text))

Max Activating Token Index: 817

Text #14

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0430. Min Act: -0.0003

Data Index: 1133491 (C4 (Web Text))

Max Activating Token Index: 250

Text #15

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0447. Min Act: -0.0003

Data Index: 88982 (C4 (Web Text))

Max Activating Token Index: 415

Text #16

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0445. Min Act: -0.0003

Data Index: 1332710 (C4 (Web Text))

Max Activating Token Index: 582

Text #17

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0425. Min Act: -0.0003

Data Index: 454089 (C4 (Web Text))

Max Activating Token Index: 196

Text #18

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0457. Min Act: -0.0003

Data Index: 1236498 (C4 (Web Text))

Max Activating Token Index: 713

Text #19

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0434. Min Act: -0.0003

Data Index: 171586 (C4 (Web Text))

Max Activating Token Index: 144