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

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

Neuron 556 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9985. Min Range: -1.9985

Max Act: 1.9985. Min Act: -0.0001

Data Index: 527349 (C4 (Web Text))

Max Activating Token Index: 350

Text #1

Max Range: 1.9985. Min Range: -1.9985

Max Act: 1.9792. Min Act: -0.0001

Data Index: 860352 (C4 (Web Text))

Max Activating Token Index: 389

Text #2

Max Range: 1.9985. Min Range: -1.9985

Max Act: 1.7811. Min Act: -0.0001

Data Index: 1049802 (C4 (Web Text))

Max Activating Token Index: 279

Text #3

Max Range: 1.9985. Min Range: -1.9985

Max Act: 1.9228. Min Act: -0.0001

Data Index: 889694 (C4 (Web Text))

Max Activating Token Index: 426

Text #4

Max Range: 1.9985. Min Range: -1.9985

Max Act: 1.5865. Min Act: -0.0001

Data Index: 525542 (C4 (Web Text))

Max Activating Token Index: 765

Text #5

Max Range: 1.9985. Min Range: -1.9985

Max Act: 1.9625. Min Act: -0.0001

Data Index: 111757 (C4 (Web Text))

Max Activating Token Index: 785

Text #6

Max Range: 1.9985. Min Range: -1.9985

Max Act: 1.9076. Min Act: -0.0001

Data Index: 171036 (C4 (Web Text))

Max Activating Token Index: 603

Text #7

Max Range: 1.9985. Min Range: -1.9985

Max Act: 1.6108. Min Act: -0.0001

Data Index: 473269 (C4 (Web Text))

Max Activating Token Index: 353

Text #8

Max Range: 1.9985. Min Range: -1.9985

Max Act: 1.6654. Min Act: -0.0001

Data Index: 414310 (C4 (Web Text))

Max Activating Token Index: 732

Text #9

Max Range: 1.9985. Min Range: -1.9985

Max Act: 1.4633. Min Act: -0.0001

Data Index: 334979 (C4 (Web Text))

Max Activating Token Index: 825

Text #10

Max Range: 1.9985. Min Range: -1.9985

Max Act: 1.4542. Min Act: -0.0001

Data Index: 1245335 (C4 (Web Text))

Max Activating Token Index: 41

Text #11

Max Range: 1.9985. Min Range: -1.9985

Max Act: 1.2515. Min Act: -0.0001

Data Index: 753165 (C4 (Web Text))

Max Activating Token Index: 472

Text #12

Max Range: 1.9985. Min Range: -1.9985

Max Act: 1.3899. Min Act: -0.0001

Data Index: 1247871 (C4 (Web Text))

Max Activating Token Index: 591

Text #13

Max Range: 1.9985. Min Range: -1.9985

Max Act: 1.3068. Min Act: -0.0001

Data Index: 1020554 (C4 (Web Text))

Max Activating Token Index: 667

Text #14

Max Range: 1.9985. Min Range: -1.9985

Max Act: 1.2751. Min Act: -0.0001

Data Index: 355010 (C4 (Web Text))

Max Activating Token Index: 554

Text #15

Max Range: 1.9985. Min Range: -1.9985

Max Act: 1.3983. Min Act: -0.0001

Data Index: 713561 (C4 (Web Text))

Max Activating Token Index: 710

Text #16

Max Range: 1.9985. Min Range: -1.9985

Max Act: 1.2416. Min Act: -0.0001

Data Index: 594641 (C4 (Web Text))

Max Activating Token Index: 375

Text #17

Max Range: 1.9985. Min Range: -1.9985

Max Act: 1.2990. Min Act: -0.0001

Data Index: 309384 (C4 (Web Text))

Max Activating Token Index: 436

Text #18

Max Range: 1.9985. Min Range: -1.9985

Max Act: 1.2402. Min Act: -0.0001

Data Index: 1132668 (C4 (Web Text))

Max Activating Token Index: 793

Text #19

Max Range: 1.9985. Min Range: -1.9985

Max Act: 1.4651. Min Act: -0.0001

Data Index: 945884 (C4 (Web Text))

Max Activating Token Index: 804