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

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

Neuron 2131 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1474. Min Range: -1.1474

Max Act: 1.1474. Min Act: -0.0000

Data Index: 700241 (C4 (Web Text))

Max Activating Token Index: 384

Text #1

Max Range: 1.1474. Min Range: -1.1474

Max Act: 0.9472. Min Act: -0.0000

Data Index: 161331 (C4 (Web Text))

Max Activating Token Index: 826

Text #2

Max Range: 1.1474. Min Range: -1.1474

Max Act: 0.9211. Min Act: -0.0000

Data Index: 543944 (C4 (Web Text))

Max Activating Token Index: 586

Text #3

Max Range: 1.1474. Min Range: -1.1474

Max Act: 0.9172. Min Act: -0.0000

Data Index: 170630 (C4 (Web Text))

Max Activating Token Index: 995

Text #4

Max Range: 1.1474. Min Range: -1.1474

Max Act: 0.8386. Min Act: -0.0000

Data Index: 366868 (C4 (Web Text))

Max Activating Token Index: 291

Text #5

Max Range: 1.1474. Min Range: -1.1474

Max Act: 0.8848. Min Act: -0.0000

Data Index: 1236862 (C4 (Web Text))

Max Activating Token Index: 540

Text #6

Max Range: 1.1474. Min Range: -1.1474

Max Act: 0.8478. Min Act: -0.0000

Data Index: 1259311 (C4 (Web Text))

Max Activating Token Index: 26

Text #7

Max Range: 1.1474. Min Range: -1.1474

Max Act: 0.8419. Min Act: -0.0000

Data Index: 1207004 (C4 (Web Text))

Max Activating Token Index: 798

Text #8

Max Range: 1.1474. Min Range: -1.1474

Max Act: 0.8635. Min Act: -0.0000

Data Index: 528782 (C4 (Web Text))

Max Activating Token Index: 594

Text #9

Max Range: 1.1474. Min Range: -1.1474

Max Act: 0.8058. Min Act: -0.0000

Data Index: 159124 (C4 (Web Text))

Max Activating Token Index: 76

Text #10

Max Range: 1.1474. Min Range: -1.1474

Max Act: 0.7889. Min Act: -0.0000

Data Index: 90033 (C4 (Web Text))

Max Activating Token Index: 221

Text #11

Max Range: 1.1474. Min Range: -1.1474

Max Act: 0.7867. Min Act: -0.0000

Data Index: 199229 (C4 (Web Text))

Max Activating Token Index: 1005

Text #12

Max Range: 1.1474. Min Range: -1.1474

Max Act: 0.7792. Min Act: -0.0000

Data Index: 845620 (C4 (Web Text))

Max Activating Token Index: 49

Text #13

Max Range: 1.1474. Min Range: -1.1474

Max Act: 0.7813. Min Act: -0.0000

Data Index: 430759 (C4 (Web Text))

Max Activating Token Index: 614

Text #14

Max Range: 1.1474. Min Range: -1.1474

Max Act: 0.8206. Min Act: -0.0000

Data Index: 660634 (C4 (Web Text))

Max Activating Token Index: 349

Text #15

Max Range: 1.1474. Min Range: -1.1474

Max Act: 0.7688. Min Act: -0.0000

Data Index: 575997 (C4 (Web Text))

Max Activating Token Index: 887

Text #16

Max Range: 1.1474. Min Range: -1.1474

Max Act: 0.7680. Min Act: -0.0000

Data Index: 880167 (C4 (Web Text))

Max Activating Token Index: 31

Text #17

Max Range: 1.1474. Min Range: -1.1474

Max Act: 0.7798. Min Act: -0.0000

Data Index: 730316 (C4 (Web Text))

Max Activating Token Index: 414

Text #18

Max Range: 1.1474. Min Range: -1.1474

Max Act: 0.8069. Min Act: -0.0000

Data Index: 686740 (C4 (Web Text))

Max Activating Token Index: 362

Text #19

Max Range: 1.1474. Min Range: -1.1474

Max Act: 0.7654. Min Act: -0.0000

Data Index: 356974 (C4 (Web Text))

Max Activating Token Index: 177