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

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

Neuron 3513 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.1043. Min Range: -5.1043

Max Act: 5.1043. Min Act: -0.0000

Data Index: 1322510 (C4 (Web Text))

Max Activating Token Index: 944

Text #1

Max Range: 5.1043. Min Range: -5.1043

Max Act: 4.7815. Min Act: -0.0000

Data Index: 1210461 (C4 (Web Text))

Max Activating Token Index: 662

Text #2

Max Range: 5.1043. Min Range: -5.1043

Max Act: 4.8329. Min Act: -0.0000

Data Index: 1208449 (C4 (Web Text))

Max Activating Token Index: 1005

Text #3

Max Range: 5.1043. Min Range: -5.1043

Max Act: 4.4452. Min Act: -0.0000

Data Index: 315294 (C4 (Web Text))

Max Activating Token Index: 858

Text #4

Max Range: 5.1043. Min Range: -5.1043

Max Act: 4.4395. Min Act: -0.0000

Data Index: 686386 (C4 (Web Text))

Max Activating Token Index: 291

Text #5

Max Range: 5.1043. Min Range: -5.1043

Max Act: 4.4523. Min Act: -0.0000

Data Index: 375670 (C4 (Web Text))

Max Activating Token Index: 561

Text #6

Max Range: 5.1043. Min Range: -5.1043

Max Act: 4.1656. Min Act: -0.0000

Data Index: 1113586 (C4 (Web Text))

Max Activating Token Index: 37

Text #7

Max Range: 5.1043. Min Range: -5.1043

Max Act: 4.4810. Min Act: -0.0000

Data Index: 1061880 (C4 (Web Text))

Max Activating Token Index: 966

Text #8

Max Range: 5.1043. Min Range: -5.1043

Max Act: 4.4755. Min Act: -0.0000

Data Index: 766588 (C4 (Web Text))

Max Activating Token Index: 955

Text #9

Max Range: 5.1043. Min Range: -5.1043

Max Act: 4.4084. Min Act: -0.0000

Data Index: 842459 (C4 (Web Text))

Max Activating Token Index: 912

Text #10

Max Range: 5.1043. Min Range: -5.1043

Max Act: 4.1436. Min Act: -0.0000

Data Index: 1328445 (C4 (Web Text))

Max Activating Token Index: 558

Text #11

Max Range: 5.1043. Min Range: -5.1043

Max Act: 4.3859. Min Act: -0.0000

Data Index: 331480 (C4 (Web Text))

Max Activating Token Index: 310

Text #12

Max Range: 5.1043. Min Range: -5.1043

Max Act: 3.8675. Min Act: -0.0000

Data Index: 152616 (C4 (Web Text))

Max Activating Token Index: 541

Text #13

Max Range: 5.1043. Min Range: -5.1043

Max Act: 4.2008. Min Act: -0.0000

Data Index: 649860 (C4 (Web Text))

Max Activating Token Index: 958

Text #14

Max Range: 5.1043. Min Range: -5.1043

Max Act: 3.9943. Min Act: -0.0000

Data Index: 1350403 (C4 (Web Text))

Max Activating Token Index: 954

Text #15

Max Range: 5.1043. Min Range: -5.1043

Max Act: 3.9715. Min Act: -0.0000

Data Index: 136918 (C4 (Web Text))

Max Activating Token Index: 592

Text #16

Max Range: 5.1043. Min Range: -5.1043

Max Act: 3.9595. Min Act: -0.0000

Data Index: 659216 (C4 (Web Text))

Max Activating Token Index: 703

Text #17

Max Range: 5.1043. Min Range: -5.1043

Max Act: 3.9374. Min Act: -0.0000

Data Index: 113683 (C4 (Web Text))

Max Activating Token Index: 34

Text #18

Max Range: 5.1043. Min Range: -5.1043

Max Act: 3.8932. Min Act: -0.0000

Data Index: 652769 (C4 (Web Text))

Max Activating Token Index: 269

Text #19

Max Range: 5.1043. Min Range: -5.1043

Max Act: 4.0502. Min Act: -0.0000

Data Index: 633206 (C4 (Web Text))

Max Activating Token Index: 911