Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.5580. Min Range: -0.5580

Max Act: 0.5580. Min Act: -0.0002

Data Index: 247230 (C4 (Web Text))

Max Activating Token Index: 831

Text #1

Max Range: 0.5580. Min Range: -0.5580

Max Act: 0.4969. Min Act: -0.0002

Data Index: 804494 (C4 (Web Text))

Max Activating Token Index: 158

Text #2

Max Range: 0.5580. Min Range: -0.5580

Max Act: 0.4731. Min Act: -0.0001

Data Index: 181361 (C4 (Web Text))

Max Activating Token Index: 976

Text #3

Max Range: 0.5580. Min Range: -0.5580

Max Act: 0.4609. Min Act: -0.0001

Data Index: 662999 (C4 (Web Text))

Max Activating Token Index: 468

Text #4

Max Range: 0.5580. Min Range: -0.5580

Max Act: 0.4557. Min Act: -0.0001

Data Index: 176671 (C4 (Web Text))

Max Activating Token Index: 696

Text #5

Max Range: 0.5580. Min Range: -0.5580

Max Act: 0.4721. Min Act: -0.0002

Data Index: 1081684 (C4 (Web Text))

Max Activating Token Index: 1000

Text #6

Max Range: 0.5580. Min Range: -0.5580

Max Act: 0.4740. Min Act: -0.0001

Data Index: 422373 (C4 (Web Text))

Max Activating Token Index: 151

Text #7

Max Range: 0.5580. Min Range: -0.5580

Max Act: 0.4689. Min Act: -0.0002

Data Index: 346353 (C4 (Web Text))

Max Activating Token Index: 86

Text #8

Max Range: 0.5580. Min Range: -0.5580

Max Act: 0.4719. Min Act: -0.0001

Data Index: 761505 (C4 (Web Text))

Max Activating Token Index: 386

Text #9

Max Range: 0.5580. Min Range: -0.5580

Max Act: 0.4599. Min Act: -0.0002

Data Index: 478730 (C4 (Web Text))

Max Activating Token Index: 715

Text #10

Max Range: 0.5580. Min Range: -0.5580

Max Act: 0.4431. Min Act: -0.0001

Data Index: 414891 (C4 (Web Text))

Max Activating Token Index: 908

Text #11

Max Range: 0.5580. Min Range: -0.5580

Max Act: 0.4535. Min Act: -0.0001

Data Index: 736255 (C4 (Web Text))

Max Activating Token Index: 757

Text #12

Max Range: 0.5580. Min Range: -0.5580

Max Act: 0.4816. Min Act: -0.0002

Data Index: 1229655 (C4 (Web Text))

Max Activating Token Index: 887

Text #13

Max Range: 0.5580. Min Range: -0.5580

Max Act: 0.4508. Min Act: -0.0002

Data Index: 1079406 (C4 (Web Text))

Max Activating Token Index: 506

Text #14

Max Range: 0.5580. Min Range: -0.5580

Max Act: 0.4428. Min Act: -0.0001

Data Index: 765547 (C4 (Web Text))

Max Activating Token Index: 642

Text #15

Max Range: 0.5580. Min Range: -0.5580

Max Act: 0.4419. Min Act: -0.0002

Data Index: 302253 (C4 (Web Text))

Max Activating Token Index: 201

Text #16

Max Range: 0.5580. Min Range: -0.5580

Max Act: 0.4365. Min Act: -0.0002

Data Index: 536057 (C4 (Web Text))

Max Activating Token Index: 123

Text #17

Max Range: 0.5580. Min Range: -0.5580

Max Act: 0.4080. Min Act: -0.0002

Data Index: 633328 (C4 (Web Text))

Max Activating Token Index: 617

Text #18

Max Range: 0.5580. Min Range: -0.5580

Max Act: 0.4445. Min Act: -0.0002

Data Index: 7501 (C4 (Web Text))

Max Activating Token Index: 981

Text #19

Max Range: 0.5580. Min Range: -0.5580

Max Act: 0.4357. Min Act: -0.0002

Data Index: 689846 (C4 (Web Text))

Max Activating Token Index: 91