Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4181 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.1089. Min Act: -0.0002

Data Index: 748451 (C4 (Web Text))

Max Activating Token Index: 693

Text #1

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.0663. Min Act: -0.0002

Data Index: 694700 (C4 (Web Text))

Max Activating Token Index: 629

Text #2

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.0642. Min Act: -0.0002

Data Index: 1319709 (C4 (Web Text))

Max Activating Token Index: 463

Text #3

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.0593. Min Act: -0.0002

Data Index: 403148 (C4 (Web Text))

Max Activating Token Index: 781

Text #4

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.0634. Min Act: -0.0002

Data Index: 1258694 (C4 (Web Text))

Max Activating Token Index: 298

Text #5

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.0596. Min Act: -0.0002

Data Index: 1059070 (C4 (Web Text))

Max Activating Token Index: 662

Text #6

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.0546. Min Act: -0.0002

Data Index: 68513 (C4 (Web Text))

Max Activating Token Index: 417

Text #7

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.0572. Min Act: -0.0002

Data Index: 233514 (C4 (Web Text))

Max Activating Token Index: 634

Text #8

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.0528. Min Act: -0.0002

Data Index: 13114 (C4 (Web Text))

Max Activating Token Index: 114

Text #9

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.0563. Min Act: -0.0002

Data Index: 291542 (C4 (Web Text))

Max Activating Token Index: 345

Text #10

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.0552. Min Act: -0.0002

Data Index: 1032049 (C4 (Web Text))

Max Activating Token Index: 505

Text #11

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.0534. Min Act: -0.0002

Data Index: 923288 (C4 (Web Text))

Max Activating Token Index: 471

Text #12

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.0554. Min Act: -0.0002

Data Index: 434951 (C4 (Web Text))

Max Activating Token Index: 782

Text #13

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.0553. Min Act: -0.0002

Data Index: 1320825 (C4 (Web Text))

Max Activating Token Index: 834

Text #14

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.0534. Min Act: -0.0002

Data Index: 263935 (C4 (Web Text))

Max Activating Token Index: 79

Text #15

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.0545. Min Act: -0.0002

Data Index: 769341 (C4 (Web Text))

Max Activating Token Index: 889

Text #16

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.0496. Min Act: -0.0002

Data Index: 290978 (C4 (Web Text))

Max Activating Token Index: 72

Text #17

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.0528. Min Act: -0.0002

Data Index: 757806 (C4 (Web Text))

Max Activating Token Index: 815

Text #18

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.0518. Min Act: -0.0002

Data Index: 1116704 (C4 (Web Text))

Max Activating Token Index: 740

Text #19

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.0520. Min Act: -0.0002

Data Index: 1220985 (C4 (Web Text))

Max Activating Token Index: 45