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

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

Neuron 2830 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6611. Min Range: -0.6611

Max Act: 0.6611. Min Act: -0.0000

Data Index: 242632 (C4 (Web Text))

Max Activating Token Index: 20

Text #1

Max Range: 0.6611. Min Range: -0.6611

Max Act: 0.6125. Min Act: -0.0000

Data Index: 280278 (C4 (Web Text))

Max Activating Token Index: 693

Text #2

Max Range: 0.6611. Min Range: -0.6611

Max Act: 0.6112. Min Act: -0.0000

Data Index: 493338 (C4 (Web Text))

Max Activating Token Index: 846

Text #3

Max Range: 0.6611. Min Range: -0.6611

Max Act: 0.5514. Min Act: -0.0000

Data Index: 561206 (C4 (Web Text))

Max Activating Token Index: 901

Text #4

Max Range: 0.6611. Min Range: -0.6611

Max Act: 0.5350. Min Act: -0.0000

Data Index: 99810 (C4 (Web Text))

Max Activating Token Index: 991

Text #5

Max Range: 0.6611. Min Range: -0.6611

Max Act: 0.5226. Min Act: -0.0000

Data Index: 361712 (C4 (Web Text))

Max Activating Token Index: 778

Text #6

Max Range: 0.6611. Min Range: -0.6611

Max Act: 0.5205. Min Act: -0.0000

Data Index: 910031 (C4 (Web Text))

Max Activating Token Index: 789

Text #7

Max Range: 0.6611. Min Range: -0.6611

Max Act: 0.4991. Min Act: -0.0000

Data Index: 1213843 (C4 (Web Text))

Max Activating Token Index: 527

Text #8

Max Range: 0.6611. Min Range: -0.6611

Max Act: 0.4776. Min Act: -0.0000

Data Index: 554234 (C4 (Web Text))

Max Activating Token Index: 724

Text #9

Max Range: 0.6611. Min Range: -0.6611

Max Act: 0.4705. Min Act: -0.0000

Data Index: 394510 (C4 (Web Text))

Max Activating Token Index: 798

Text #10

Max Range: 0.6611. Min Range: -0.6611

Max Act: 0.4654. Min Act: -0.0000

Data Index: 113971 (C4 (Web Text))

Max Activating Token Index: 489

Text #11

Max Range: 0.6611. Min Range: -0.6611

Max Act: 0.4790. Min Act: -0.0000

Data Index: 1234220 (C4 (Web Text))

Max Activating Token Index: 299

Text #12

Max Range: 0.6611. Min Range: -0.6611

Max Act: 0.4727. Min Act: -0.0000

Data Index: 743592 (C4 (Web Text))

Max Activating Token Index: 476

Text #13

Max Range: 0.6611. Min Range: -0.6611

Max Act: 0.4881. Min Act: -0.0000

Data Index: 152086 (C4 (Web Text))

Max Activating Token Index: 92

Text #14

Max Range: 0.6611. Min Range: -0.6611

Max Act: 0.4550. Min Act: -0.0000

Data Index: 336606 (C4 (Web Text))

Max Activating Token Index: 1002

Text #15

Max Range: 0.6611. Min Range: -0.6611

Max Act: 0.4849. Min Act: -0.0000

Data Index: 729889 (C4 (Web Text))

Max Activating Token Index: 745

Text #16

Max Range: 0.6611. Min Range: -0.6611

Max Act: 0.4658. Min Act: -0.0000

Data Index: 198520 (C4 (Web Text))

Max Activating Token Index: 645

Text #17

Max Range: 0.6611. Min Range: -0.6611

Max Act: 0.4497. Min Act: -0.0000

Data Index: 1102883 (C4 (Web Text))

Max Activating Token Index: 88

Text #18

Max Range: 0.6611. Min Range: -0.6611

Max Act: 0.4812. Min Act: -0.0000

Data Index: 456619 (C4 (Web Text))

Max Activating Token Index: 755

Text #19

Max Range: 0.6611. Min Range: -0.6611

Max Act: 0.4503. Min Act: -0.0000

Data Index: 101863 (C4 (Web Text))

Max Activating Token Index: 757