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

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

Neuron 1697 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6595. Min Range: -0.6595

Max Act: 0.6595. Min Act: -0.0000

Data Index: 870382 (C4 (Web Text))

Max Activating Token Index: 325

Text #1

Max Range: 0.6595. Min Range: -0.6595

Max Act: 0.6574. Min Act: -0.0001

Data Index: 991586 (C4 (Web Text))

Max Activating Token Index: 603

Text #2

Max Range: 0.6595. Min Range: -0.6595

Max Act: 0.5582. Min Act: -0.0000

Data Index: 625284 (C4 (Web Text))

Max Activating Token Index: 365

Text #3

Max Range: 0.6595. Min Range: -0.6595

Max Act: 0.5738. Min Act: -0.0001

Data Index: 449923 (C4 (Web Text))

Max Activating Token Index: 771

Text #4

Max Range: 0.6595. Min Range: -0.6595

Max Act: 0.5503. Min Act: -0.0000

Data Index: 707340 (C4 (Web Text))

Max Activating Token Index: 566

Text #5

Max Range: 0.6595. Min Range: -0.6595

Max Act: 0.5503. Min Act: -0.0000

Data Index: 41057 (C4 (Web Text))

Max Activating Token Index: 338

Text #6

Max Range: 0.6595. Min Range: -0.6595

Max Act: 0.5701. Min Act: -0.0001

Data Index: 646669 (C4 (Web Text))

Max Activating Token Index: 501

Text #7

Max Range: 0.6595. Min Range: -0.6595

Max Act: 0.5480. Min Act: -0.0000

Data Index: 186933 (C4 (Web Text))

Max Activating Token Index: 355

Text #8

Max Range: 0.6595. Min Range: -0.6595

Max Act: 0.5496. Min Act: -0.0001

Data Index: 846162 (C4 (Web Text))

Max Activating Token Index: 882

Text #9

Max Range: 0.6595. Min Range: -0.6595

Max Act: 0.5461. Min Act: -0.0001

Data Index: 429984 (C4 (Web Text))

Max Activating Token Index: 658

Text #10

Max Range: 0.6595. Min Range: -0.6595

Max Act: 0.5411. Min Act: -0.0000

Data Index: 417347 (C4 (Web Text))

Max Activating Token Index: 790

Text #11

Max Range: 0.6595. Min Range: -0.6595

Max Act: 0.5411. Min Act: -0.0001

Data Index: 627675 (C4 (Web Text))

Max Activating Token Index: 564

Text #12

Max Range: 0.6595. Min Range: -0.6595

Max Act: 0.5376. Min Act: -0.0000

Data Index: 1101081 (C4 (Web Text))

Max Activating Token Index: 1000

Text #13

Max Range: 0.6595. Min Range: -0.6595

Max Act: 0.5316. Min Act: -0.0000

Data Index: 1076727 (C4 (Web Text))

Max Activating Token Index: 567

Text #14

Max Range: 0.6595. Min Range: -0.6595

Max Act: 0.5253. Min Act: -0.0000

Data Index: 102067 (C4 (Web Text))

Max Activating Token Index: 815

Text #15

Max Range: 0.6595. Min Range: -0.6595

Max Act: 0.4859. Min Act: -0.0000

Data Index: 723023 (C4 (Web Text))

Max Activating Token Index: 94

Text #16

Max Range: 0.6595. Min Range: -0.6595

Max Act: 0.4909. Min Act: -0.0000

Data Index: 1097545 (C4 (Web Text))

Max Activating Token Index: 887

Text #17

Max Range: 0.6595. Min Range: -0.6595

Max Act: 0.5020. Min Act: -0.0000

Data Index: 36141 (C4 (Web Text))

Max Activating Token Index: 950

Text #18

Max Range: 0.6595. Min Range: -0.6595

Max Act: 0.4751. Min Act: -0.0000

Data Index: 66628 (C4 (Web Text))

Max Activating Token Index: 233

Text #19

Max Range: 0.6595. Min Range: -0.6595

Max Act: 0.4901. Min Act: -0.0001

Data Index: 129481 (C4 (Web Text))

Max Activating Token Index: 540