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

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

Neuron 4617 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9724. Min Range: -2.9724

Max Act: 2.8719. Min Act: -0.0001

Data Index: 332328 (C4 (Web Text))

Max Activating Token Index: 29

Text #1

Max Range: 2.9724. Min Range: -2.9724

Max Act: 2.9724. Min Act: -0.0001

Data Index: 707204 (C4 (Web Text))

Max Activating Token Index: 143

Text #2

Max Range: 2.9724. Min Range: -2.9724

Max Act: 2.5149. Min Act: -0.0000

Data Index: 288900 (C4 (Web Text))

Max Activating Token Index: 13

Text #3

Max Range: 2.9724. Min Range: -2.9724

Max Act: 2.6354. Min Act: -0.0000

Data Index: 1198641 (C4 (Web Text))

Max Activating Token Index: 189

Text #4

Max Range: 2.9724. Min Range: -2.9724

Max Act: 2.5281. Min Act: -0.0000

Data Index: 1116029 (C4 (Web Text))

Max Activating Token Index: 66

Text #5

Max Range: 2.9724. Min Range: -2.9724

Max Act: 2.4890. Min Act: -0.0001

Data Index: 586282 (C4 (Web Text))

Max Activating Token Index: 13

Text #6

Max Range: 2.9724. Min Range: -2.9724

Max Act: 2.6029. Min Act: -0.0000

Data Index: 545339 (C4 (Web Text))

Max Activating Token Index: 199

Text #7

Max Range: 2.9724. Min Range: -2.9724

Max Act: 2.5654. Min Act: -0.0001

Data Index: 1328318 (C4 (Web Text))

Max Activating Token Index: 433

Text #8

Max Range: 2.9724. Min Range: -2.9724

Max Act: 2.5373. Min Act: -0.0000

Data Index: 819552 (C4 (Web Text))

Max Activating Token Index: 603

Text #9

Max Range: 2.9724. Min Range: -2.9724

Max Act: 2.6676. Min Act: -0.0000

Data Index: 242771 (C4 (Web Text))

Max Activating Token Index: 745

Text #10

Max Range: 2.9724. Min Range: -2.9724

Max Act: 2.3814. Min Act: -0.0000

Data Index: 79245 (C4 (Web Text))

Max Activating Token Index: 705

Text #11

Max Range: 2.9724. Min Range: -2.9724

Max Act: 2.5116. Min Act: -0.0000

Data Index: 345349 (C4 (Web Text))

Max Activating Token Index: 558

Text #12

Max Range: 2.9724. Min Range: -2.9724

Max Act: 2.3382. Min Act: -0.0001

Data Index: 1267714 (C4 (Web Text))

Max Activating Token Index: 990

Text #13

Max Range: 2.9724. Min Range: -2.9724

Max Act: 2.2238. Min Act: -0.0000

Data Index: 1035807 (C4 (Web Text))

Max Activating Token Index: 760

Text #14

Max Range: 2.9724. Min Range: -2.9724

Max Act: 2.3121. Min Act: -0.0001

Data Index: 103153 (C4 (Web Text))

Max Activating Token Index: 85

Text #15

Max Range: 2.9724. Min Range: -2.9724

Max Act: 2.6349. Min Act: -0.0001

Data Index: 372788 (C4 (Web Text))

Max Activating Token Index: 782

Text #16

Max Range: 2.9724. Min Range: -2.9724

Max Act: 2.1602. Min Act: -0.0000

Data Index: 684266 (C4 (Web Text))

Max Activating Token Index: 458

Text #17

Max Range: 2.9724. Min Range: -2.9724

Max Act: 2.3488. Min Act: -0.0000

Data Index: 114303 (C4 (Web Text))

Max Activating Token Index: 318

Text #18

Max Range: 2.9724. Min Range: -2.9724

Max Act: 2.3552. Min Act: -0.0001

Data Index: 476884 (C4 (Web Text))

Max Activating Token Index: 759

Text #19

Max Range: 2.9724. Min Range: -2.9724

Max Act: 2.0830. Min Act: -0.0000

Data Index: 1316049 (C4 (Web Text))

Max Activating Token Index: 479