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

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

Neuron 1736 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3640. Min Range: -0.3640

Max Act: 0.3543. Min Act: -0.0000

Data Index: 1207087 (C4 (Web Text))

Max Activating Token Index: 806

Text #1

Max Range: 0.3640. Min Range: -0.3640

Max Act: 0.3382. Min Act: -0.0000

Data Index: 1041721 (C4 (Web Text))

Max Activating Token Index: 121

Text #2

Max Range: 0.3640. Min Range: -0.3640

Max Act: 0.3640. Min Act: -0.0000

Data Index: 910793 (C4 (Web Text))

Max Activating Token Index: 882

Text #3

Max Range: 0.3640. Min Range: -0.3640

Max Act: 0.3258. Min Act: -0.0000

Data Index: 700436 (C4 (Web Text))

Max Activating Token Index: 306

Text #4

Max Range: 0.3640. Min Range: -0.3640

Max Act: 0.3024. Min Act: -0.0000

Data Index: 660955 (C4 (Web Text))

Max Activating Token Index: 635

Text #5

Max Range: 0.3640. Min Range: -0.3640

Max Act: 0.2860. Min Act: -0.0000

Data Index: 970059 (C4 (Web Text))

Max Activating Token Index: 549

Text #6

Max Range: 0.3640. Min Range: -0.3640

Max Act: 0.2833. Min Act: -0.0000

Data Index: 390940 (C4 (Web Text))

Max Activating Token Index: 471

Text #7

Max Range: 0.3640. Min Range: -0.3640

Max Act: 0.2650. Min Act: -0.0000

Data Index: 1246579 (C4 (Web Text))

Max Activating Token Index: 889

Text #8

Max Range: 0.3640. Min Range: -0.3640

Max Act: 0.2669. Min Act: -0.0000

Data Index: 1315157 (C4 (Web Text))

Max Activating Token Index: 463

Text #9

Max Range: 0.3640. Min Range: -0.3640

Max Act: 0.2750. Min Act: -0.0000

Data Index: 238441 (C4 (Web Text))

Max Activating Token Index: 753

Text #10

Max Range: 0.3640. Min Range: -0.3640

Max Act: 0.2632. Min Act: -0.0000

Data Index: 145948 (C4 (Web Text))

Max Activating Token Index: 782

Text #11

Max Range: 0.3640. Min Range: -0.3640

Max Act: 0.2691. Min Act: -0.0000

Data Index: 65982 (C4 (Web Text))

Max Activating Token Index: 66

Text #12

Max Range: 0.3640. Min Range: -0.3640

Max Act: 0.2760. Min Act: -0.0000

Data Index: 965710 (C4 (Web Text))

Max Activating Token Index: 312

Text #13

Max Range: 0.3640. Min Range: -0.3640

Max Act: 0.2790. Min Act: -0.0000

Data Index: 79727 (C4 (Web Text))

Max Activating Token Index: 602

Text #14

Max Range: 0.3640. Min Range: -0.3640

Max Act: 0.2688. Min Act: -0.0000

Data Index: 1060073 (C4 (Web Text))

Max Activating Token Index: 922

Text #15

Max Range: 0.3640. Min Range: -0.3640

Max Act: 0.2718. Min Act: -0.0000

Data Index: 1347541 (C4 (Web Text))

Max Activating Token Index: 614

Text #16

Max Range: 0.3640. Min Range: -0.3640

Max Act: 0.2528. Min Act: -0.0000

Data Index: 94527 (C4 (Web Text))

Max Activating Token Index: 113

Text #17

Max Range: 0.3640. Min Range: -0.3640

Max Act: 0.2500. Min Act: -0.0000

Data Index: 805279 (C4 (Web Text))

Max Activating Token Index: 75

Text #18

Max Range: 0.3640. Min Range: -0.3640

Max Act: 0.2609. Min Act: -0.0000

Data Index: 923456 (C4 (Web Text))

Max Activating Token Index: 646

Text #19

Max Range: 0.3640. Min Range: -0.3640

Max Act: 0.2581. Min Act: -0.0000

Data Index: 19422 (C4 (Web Text))

Max Activating Token Index: 222