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

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

Neuron 446 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7423. Min Range: -1.7423

Max Act: 1.7423. Min Act: -0.0000

Data Index: 115791 (C4 (Web Text))

Max Activating Token Index: 891

Text #1

Max Range: 1.7423. Min Range: -1.7423

Max Act: 1.6227. Min Act: -0.0000

Data Index: 454200 (C4 (Web Text))

Max Activating Token Index: 162

Text #2

Max Range: 1.7423. Min Range: -1.7423

Max Act: 1.6044. Min Act: -0.0000

Data Index: 1269446 (C4 (Web Text))

Max Activating Token Index: 947

Text #3

Max Range: 1.7423. Min Range: -1.7423

Max Act: 1.5725. Min Act: -0.0000

Data Index: 464311 (C4 (Web Text))

Max Activating Token Index: 842

Text #4

Max Range: 1.7423. Min Range: -1.7423

Max Act: 1.5019. Min Act: -0.0000

Data Index: 535446 (C4 (Web Text))

Max Activating Token Index: 256

Text #5

Max Range: 1.7423. Min Range: -1.7423

Max Act: 1.2639. Min Act: -0.0000

Data Index: 1353397 (C4 (Web Text))

Max Activating Token Index: 696

Text #6

Max Range: 1.7423. Min Range: -1.7423

Max Act: 1.2341. Min Act: -0.0000

Data Index: 45763 (C4 (Web Text))

Max Activating Token Index: 36

Text #7

Max Range: 1.7423. Min Range: -1.7423

Max Act: 1.2282. Min Act: -0.0000

Data Index: 990530 (C4 (Web Text))

Max Activating Token Index: 684

Text #8

Max Range: 1.7423. Min Range: -1.7423

Max Act: 1.2430. Min Act: -0.0000

Data Index: 177481 (C4 (Web Text))

Max Activating Token Index: 713

Text #9

Max Range: 1.7423. Min Range: -1.7423

Max Act: 1.1676. Min Act: -0.0000

Data Index: 675415 (C4 (Web Text))

Max Activating Token Index: 194

Text #10

Max Range: 1.7423. Min Range: -1.7423

Max Act: 1.0876. Min Act: -0.0000

Data Index: 249647 (C4 (Web Text))

Max Activating Token Index: 758

Text #11

Max Range: 1.7423. Min Range: -1.7423

Max Act: 1.1890. Min Act: -0.0000

Data Index: 546480 (C4 (Web Text))

Max Activating Token Index: 1012

Text #12

Max Range: 1.7423. Min Range: -1.7423

Max Act: 1.1714. Min Act: -0.0000

Data Index: 294340 (C4 (Web Text))

Max Activating Token Index: 495

Text #13

Max Range: 1.7423. Min Range: -1.7423

Max Act: 1.1782. Min Act: -0.0000

Data Index: 164447 (C4 (Web Text))

Max Activating Token Index: 305

Text #14

Max Range: 1.7423. Min Range: -1.7423

Max Act: 1.0914. Min Act: -0.0000

Data Index: 1053869 (C4 (Web Text))

Max Activating Token Index: 802

Text #15

Max Range: 1.7423. Min Range: -1.7423

Max Act: 1.1609. Min Act: -0.0000

Data Index: 787857 (C4 (Web Text))

Max Activating Token Index: 813

Text #16

Max Range: 1.7423. Min Range: -1.7423

Max Act: 1.1106. Min Act: -0.0000

Data Index: 1052088 (C4 (Web Text))

Max Activating Token Index: 991

Text #17

Max Range: 1.7423. Min Range: -1.7423

Max Act: 1.1276. Min Act: -0.0000

Data Index: 438888 (C4 (Web Text))

Max Activating Token Index: 346

Text #18

Max Range: 1.7423. Min Range: -1.7423

Max Act: 1.0579. Min Act: -0.0000

Data Index: 392733 (C4 (Web Text))

Max Activating Token Index: 19

Text #19

Max Range: 1.7423. Min Range: -1.7423

Max Act: 1.0817. Min Act: -0.0000

Data Index: 150484 (C4 (Web Text))

Max Activating Token Index: 101