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

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

Neuron 1584 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6995. Min Range: -1.6995

Max Act: 1.6849. Min Act: -0.0001

Data Index: 824198 (C4 (Web Text))

Max Activating Token Index: 724

Text #1

Max Range: 1.6995. Min Range: -1.6995

Max Act: 1.6995. Min Act: -0.0000

Data Index: 1176333 (C4 (Web Text))

Max Activating Token Index: 391

Text #2

Max Range: 1.6995. Min Range: -1.6995

Max Act: 1.5865. Min Act: -0.0001

Data Index: 104918 (C4 (Web Text))

Max Activating Token Index: 506

Text #3

Max Range: 1.6995. Min Range: -1.6995

Max Act: 1.6569. Min Act: -0.0001

Data Index: 870707 (C4 (Web Text))

Max Activating Token Index: 530

Text #4

Max Range: 1.6995. Min Range: -1.6995

Max Act: 1.5605. Min Act: -0.0001

Data Index: 683441 (C4 (Web Text))

Max Activating Token Index: 565

Text #5

Max Range: 1.6995. Min Range: -1.6995

Max Act: 1.5486. Min Act: -0.0001

Data Index: 423836 (C4 (Web Text))

Max Activating Token Index: 977

Text #6

Max Range: 1.6995. Min Range: -1.6995

Max Act: 1.5375. Min Act: -0.0001

Data Index: 317277 (C4 (Web Text))

Max Activating Token Index: 474

Text #7

Max Range: 1.6995. Min Range: -1.6995

Max Act: 1.5498. Min Act: -0.0001

Data Index: 78553 (C4 (Web Text))

Max Activating Token Index: 743

Text #8

Max Range: 1.6995. Min Range: -1.6995

Max Act: 1.5857. Min Act: -0.0000

Data Index: 1142457 (C4 (Web Text))

Max Activating Token Index: 530

Text #9

Max Range: 1.6995. Min Range: -1.6995

Max Act: 1.4709. Min Act: -0.0001

Data Index: 907261 (C4 (Web Text))

Max Activating Token Index: 811

Text #10

Max Range: 1.6995. Min Range: -1.6995

Max Act: 1.4964. Min Act: -0.0001

Data Index: 1080578 (C4 (Web Text))

Max Activating Token Index: 925

Text #11

Max Range: 1.6995. Min Range: -1.6995

Max Act: 1.4755. Min Act: -0.0001

Data Index: 57308 (C4 (Web Text))

Max Activating Token Index: 282

Text #12

Max Range: 1.6995. Min Range: -1.6995

Max Act: 1.4987. Min Act: -0.0001

Data Index: 997831 (C4 (Web Text))

Max Activating Token Index: 402

Text #13

Max Range: 1.6995. Min Range: -1.6995

Max Act: 1.4548. Min Act: -0.0001

Data Index: 291352 (C4 (Web Text))

Max Activating Token Index: 490

Text #14

Max Range: 1.6995. Min Range: -1.6995

Max Act: 1.4965. Min Act: -0.0001

Data Index: 848467 (C4 (Web Text))

Max Activating Token Index: 752

Text #15

Max Range: 1.6995. Min Range: -1.6995

Max Act: 1.4530. Min Act: -0.0001

Data Index: 905247 (C4 (Web Text))

Max Activating Token Index: 957

Text #16

Max Range: 1.6995. Min Range: -1.6995

Max Act: 1.4116. Min Act: -0.0001

Data Index: 794749 (C4 (Web Text))

Max Activating Token Index: 785

Text #17

Max Range: 1.6995. Min Range: -1.6995

Max Act: 1.4949. Min Act: -0.0001

Data Index: 623326 (C4 (Web Text))

Max Activating Token Index: 359

Text #18

Max Range: 1.6995. Min Range: -1.6995

Max Act: 1.4363. Min Act: -0.0001

Data Index: 742175 (C4 (Web Text))

Max Activating Token Index: 374

Text #19

Max Range: 1.6995. Min Range: -1.6995

Max Act: 1.4472. Min Act: -0.0001

Data Index: 357263 (C4 (Web Text))

Max Activating Token Index: 1000