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

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

Neuron 1720 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0554. Min Range: -0.0554

Max Act: 0.0535. Min Act: -0.0002

Data Index: 355927 (C4 (Web Text))

Max Activating Token Index: 799

Text #1

Max Range: 0.0554. Min Range: -0.0554

Max Act: 0.0506. Min Act: -0.0002

Data Index: 944179 (C4 (Web Text))

Max Activating Token Index: 769

Text #2

Max Range: 0.0554. Min Range: -0.0554

Max Act: 0.0438. Min Act: -0.0002

Data Index: 767313 (C4 (Web Text))

Max Activating Token Index: 736

Text #3

Max Range: 0.0554. Min Range: -0.0554

Max Act: 0.0554. Min Act: -0.0002

Data Index: 1101723 (C4 (Web Text))

Max Activating Token Index: 71

Text #4

Max Range: 0.0554. Min Range: -0.0554

Max Act: 0.0493. Min Act: -0.0002

Data Index: 872522 (C4 (Web Text))

Max Activating Token Index: 351

Text #5

Max Range: 0.0554. Min Range: -0.0554

Max Act: 0.0493. Min Act: -0.0002

Data Index: 736476 (C4 (Web Text))

Max Activating Token Index: 776

Text #6

Max Range: 0.0554. Min Range: -0.0554

Max Act: 0.0417. Min Act: -0.0002

Data Index: 274090 (C4 (Web Text))

Max Activating Token Index: 776

Text #7

Max Range: 0.0554. Min Range: -0.0554

Max Act: 0.0487. Min Act: -0.0002

Data Index: 518364 (C4 (Web Text))

Max Activating Token Index: 260

Text #8

Max Range: 0.0554. Min Range: -0.0554

Max Act: 0.0490. Min Act: -0.0002

Data Index: 1218659 (C4 (Web Text))

Max Activating Token Index: 42

Text #9

Max Range: 0.0554. Min Range: -0.0554

Max Act: 0.0512. Min Act: -0.0002

Data Index: 381125 (C4 (Web Text))

Max Activating Token Index: 101

Text #10

Max Range: 0.0554. Min Range: -0.0554

Max Act: 0.0498. Min Act: -0.0002

Data Index: 1058196 (C4 (Web Text))

Max Activating Token Index: 812

Text #11

Max Range: 0.0554. Min Range: -0.0554

Max Act: 0.0440. Min Act: -0.0002

Data Index: 277168 (C4 (Web Text))

Max Activating Token Index: 823

Text #12

Max Range: 0.0554. Min Range: -0.0554

Max Act: 0.0471. Min Act: -0.0002

Data Index: 1151395 (C4 (Web Text))

Max Activating Token Index: 11

Text #13

Max Range: 0.0554. Min Range: -0.0554

Max Act: 0.0437. Min Act: -0.0002

Data Index: 435371 (C4 (Web Text))

Max Activating Token Index: 31

Text #14

Max Range: 0.0554. Min Range: -0.0554

Max Act: 0.0497. Min Act: -0.0002

Data Index: 913186 (C4 (Web Text))

Max Activating Token Index: 19

Text #15

Max Range: 0.0554. Min Range: -0.0554

Max Act: 0.0464. Min Act: -0.0002

Data Index: 1209110 (C4 (Web Text))

Max Activating Token Index: 20

Text #16

Max Range: 0.0554. Min Range: -0.0554

Max Act: 0.0465. Min Act: -0.0002

Data Index: 1075334 (C4 (Web Text))

Max Activating Token Index: 22

Text #17

Max Range: 0.0554. Min Range: -0.0554

Max Act: 0.0490. Min Act: -0.0002

Data Index: 467656 (C4 (Web Text))

Max Activating Token Index: 316

Text #18

Max Range: 0.0554. Min Range: -0.0554

Max Act: 0.0461. Min Act: -0.0002

Data Index: 1242893 (C4 (Web Text))

Max Activating Token Index: 494

Text #19

Max Range: 0.0554. Min Range: -0.0554

Max Act: 0.0468. Min Act: -0.0002

Data Index: 243679 (C4 (Web Text))

Max Activating Token Index: 12