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

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

Neuron 3564 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: 2.9602. Min Range: -2.9602

Max Act: 2.6295. Min Act: -0.0000

Data Index: 1532310 (Python Code)

Max Activating Token Index: 521

Text #1

Max Range: 2.9602. Min Range: -2.9602

Max Act: 2.9602. Min Act: -0.0000

Data Index: 1406550 (Python Code)

Max Activating Token Index: 695

Text #2

Max Range: 2.9602. Min Range: -2.9602

Max Act: 2.4329. Min Act: -0.0000

Data Index: 1490027 (Python Code)

Max Activating Token Index: 842

Text #3

Max Range: 2.9602. Min Range: -2.9602

Max Act: 2.1987. Min Act: -0.0000

Data Index: 1632715 (Python Code)

Max Activating Token Index: 199

Text #4

Max Range: 2.9602. Min Range: -2.9602

Max Act: 2.4177. Min Act: -0.0000

Data Index: 1517600 (Python Code)

Max Activating Token Index: 330

Text #5

Max Range: 2.9602. Min Range: -2.9602

Max Act: 2.1447. Min Act: -0.0000

Data Index: 1436724 (Python Code)

Max Activating Token Index: 514

Text #6

Max Range: 2.9602. Min Range: -2.9602

Max Act: 2.0468. Min Act: -0.0000

Data Index: 1466610 (Python Code)

Max Activating Token Index: 884

Text #7

Max Range: 2.9602. Min Range: -2.9602

Max Act: 2.0421. Min Act: -0.0000

Data Index: 1557077 (Python Code)

Max Activating Token Index: 152

Text #8

Max Range: 2.9602. Min Range: -2.9602

Max Act: 2.0646. Min Act: -0.0000

Data Index: 1516746 (Python Code)

Max Activating Token Index: 316

Text #9

Max Range: 2.9602. Min Range: -2.9602

Max Act: 2.0447. Min Act: -0.0000

Data Index: 1451316 (Python Code)

Max Activating Token Index: 586

Text #10

Max Range: 2.9602. Min Range: -2.9602

Max Act: 1.8876. Min Act: -0.0000

Data Index: 1587658 (Python Code)

Max Activating Token Index: 636

Text #11

Max Range: 2.9602. Min Range: -2.9602

Max Act: 1.7919. Min Act: -0.0000

Data Index: 1552459 (Python Code)

Max Activating Token Index: 769

Text #12

Max Range: 2.9602. Min Range: -2.9602

Max Act: 1.8419. Min Act: -0.0000

Data Index: 1472963 (Python Code)

Max Activating Token Index: 418

Text #13

Max Range: 2.9602. Min Range: -2.9602

Max Act: 1.7384. Min Act: -0.0000

Data Index: 1472676 (Python Code)

Max Activating Token Index: 806

Text #14

Max Range: 2.9602. Min Range: -2.9602

Max Act: 1.5615. Min Act: -0.0000

Data Index: 223752 (C4 (Web Text))

Max Activating Token Index: 210

Text #15

Max Range: 2.9602. Min Range: -2.9602

Max Act: 1.5705. Min Act: -0.0000

Data Index: 1636719 (Python Code)

Max Activating Token Index: 853

Text #16

Max Range: 2.9602. Min Range: -2.9602

Max Act: 1.5199. Min Act: -0.0000

Data Index: 1444902 (Python Code)

Max Activating Token Index: 730

Text #17

Max Range: 2.9602. Min Range: -2.9602

Max Act: 1.5486. Min Act: -0.0000

Data Index: 722467 (C4 (Web Text))

Max Activating Token Index: 393

Text #18

Max Range: 2.9602. Min Range: -2.9602

Max Act: 1.6270. Min Act: -0.0000

Data Index: 909940 (C4 (Web Text))

Max Activating Token Index: 729

Text #19

Max Range: 2.9602. Min Range: -2.9602

Max Act: 1.4091. Min Act: -0.0000

Data Index: 1168328 (C4 (Web Text))

Max Activating Token Index: 523