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

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

Neuron 3815 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1724. Min Range: -2.1724

Max Act: 2.1517. Min Act: -0.0000

Data Index: 816787 (C4 (Web Text))

Max Activating Token Index: 540

Text #1

Max Range: 2.1724. Min Range: -2.1724

Max Act: 2.1275. Min Act: -0.0000

Data Index: 1266337 (C4 (Web Text))

Max Activating Token Index: 895

Text #2

Max Range: 2.1724. Min Range: -2.1724

Max Act: 1.9677. Min Act: -0.0000

Data Index: 778697 (C4 (Web Text))

Max Activating Token Index: 1021

Text #3

Max Range: 2.1724. Min Range: -2.1724

Max Act: 2.1724. Min Act: -0.0000

Data Index: 1002078 (C4 (Web Text))

Max Activating Token Index: 62

Text #4

Max Range: 2.1724. Min Range: -2.1724

Max Act: 1.8055. Min Act: -0.0000

Data Index: 1161112 (C4 (Web Text))

Max Activating Token Index: 343

Text #5

Max Range: 2.1724. Min Range: -2.1724

Max Act: 1.9937. Min Act: -0.0000

Data Index: 58247 (C4 (Web Text))

Max Activating Token Index: 723

Text #6

Max Range: 2.1724. Min Range: -2.1724

Max Act: 1.8723. Min Act: -0.0000

Data Index: 632505 (C4 (Web Text))

Max Activating Token Index: 430

Text #7

Max Range: 2.1724. Min Range: -2.1724

Max Act: 1.7528. Min Act: -0.0000

Data Index: 954540 (C4 (Web Text))

Max Activating Token Index: 249

Text #8

Max Range: 2.1724. Min Range: -2.1724

Max Act: 2.0022. Min Act: -0.0000

Data Index: 954178 (C4 (Web Text))

Max Activating Token Index: 250

Text #9

Max Range: 2.1724. Min Range: -2.1724

Max Act: 1.7486. Min Act: -0.0000

Data Index: 454395 (C4 (Web Text))

Max Activating Token Index: 538

Text #10

Max Range: 2.1724. Min Range: -2.1724

Max Act: 2.0577. Min Act: -0.0000

Data Index: 704049 (C4 (Web Text))

Max Activating Token Index: 358

Text #11

Max Range: 2.1724. Min Range: -2.1724

Max Act: 1.7892. Min Act: -0.0000

Data Index: 1205933 (C4 (Web Text))

Max Activating Token Index: 402

Text #12

Max Range: 2.1724. Min Range: -2.1724

Max Act: 1.8074. Min Act: -0.0000

Data Index: 567572 (C4 (Web Text))

Max Activating Token Index: 296

Text #13

Max Range: 2.1724. Min Range: -2.1724

Max Act: 1.9998. Min Act: -0.0000

Data Index: 1007035 (C4 (Web Text))

Max Activating Token Index: 353

Text #14

Max Range: 2.1724. Min Range: -2.1724

Max Act: 1.7735. Min Act: -0.0000

Data Index: 1117274 (C4 (Web Text))

Max Activating Token Index: 811

Text #15

Max Range: 2.1724. Min Range: -2.1724

Max Act: 1.9662. Min Act: -0.0000

Data Index: 177561 (C4 (Web Text))

Max Activating Token Index: 66

Text #16

Max Range: 2.1724. Min Range: -2.1724

Max Act: 1.6917. Min Act: -0.0000

Data Index: 442552 (C4 (Web Text))

Max Activating Token Index: 604

Text #17

Max Range: 2.1724. Min Range: -2.1724

Max Act: 1.8264. Min Act: -0.0000

Data Index: 1038302 (C4 (Web Text))

Max Activating Token Index: 352

Text #18

Max Range: 2.1724. Min Range: -2.1724

Max Act: 1.7992. Min Act: -0.0000

Data Index: 476809 (C4 (Web Text))

Max Activating Token Index: 347

Text #19

Max Range: 2.1724. Min Range: -2.1724

Max Act: 1.7932. Min Act: -0.0000

Data Index: 7259 (C4 (Web Text))

Max Activating Token Index: 578