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

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

Neuron 453 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: 0.0645. Min Range: -0.0645

Max Act: 0.0645. Min Act: -0.0003

Data Index: 1111902 (C4 (Web Text))

Max Activating Token Index: 116

Text #1

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0591. Min Act: -0.0003

Data Index: 39561 (C4 (Web Text))

Max Activating Token Index: 695

Text #2

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0627. Min Act: -0.0003

Data Index: 689213 (C4 (Web Text))

Max Activating Token Index: 13

Text #3

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0607. Min Act: -0.0003

Data Index: 1254864 (C4 (Web Text))

Max Activating Token Index: 577

Text #4

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0575. Min Act: -0.0003

Data Index: 218524 (C4 (Web Text))

Max Activating Token Index: 412

Text #5

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0561. Min Act: -0.0003

Data Index: 1179393 (C4 (Web Text))

Max Activating Token Index: 451

Text #6

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0568. Min Act: -0.0003

Data Index: 1330683 (C4 (Web Text))

Max Activating Token Index: 108

Text #7

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0574. Min Act: -0.0003

Data Index: 257730 (C4 (Web Text))

Max Activating Token Index: 486

Text #8

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0524. Min Act: -0.0003

Data Index: 215708 (C4 (Web Text))

Max Activating Token Index: 814

Text #9

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0465. Min Act: -0.0003

Data Index: 1322810 (C4 (Web Text))

Max Activating Token Index: 310

Text #10

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0508. Min Act: -0.0003

Data Index: 836989 (C4 (Web Text))

Max Activating Token Index: 378

Text #11

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0495. Min Act: -0.0003

Data Index: 714801 (C4 (Web Text))

Max Activating Token Index: 11

Text #12

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0463. Min Act: -0.0003

Data Index: 1112644 (C4 (Web Text))

Max Activating Token Index: 371

Text #13

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0495. Min Act: -0.0003

Data Index: 444403 (C4 (Web Text))

Max Activating Token Index: 837

Text #14

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0497. Min Act: -0.0003

Data Index: 98117 (C4 (Web Text))

Max Activating Token Index: 97

Text #15

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0482. Min Act: -0.0003

Data Index: 156853 (C4 (Web Text))

Max Activating Token Index: 314

Text #16

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0503. Min Act: -0.0003

Data Index: 1010648 (C4 (Web Text))

Max Activating Token Index: 362

Text #17

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0517. Min Act: -0.0003

Data Index: 766586 (C4 (Web Text))

Max Activating Token Index: 573

Text #18

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0488. Min Act: -0.0003

Data Index: 316420 (C4 (Web Text))

Max Activating Token Index: 1017

Text #19

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0476. Min Act: -0.0003

Data Index: 699466 (C4 (Web Text))

Max Activating Token Index: 485