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

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

Neuron 3716 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6445. Min Range: -0.6445

Max Act: 0.6445. Min Act: -0.0000

Data Index: 839743 (C4 (Web Text))

Max Activating Token Index: 37

Text #1

Max Range: 0.6445. Min Range: -0.6445

Max Act: 0.4620. Min Act: -0.0000

Data Index: 885439 (C4 (Web Text))

Max Activating Token Index: 141

Text #2

Max Range: 0.6445. Min Range: -0.6445

Max Act: 0.5307. Min Act: -0.0000

Data Index: 610303 (C4 (Web Text))

Max Activating Token Index: 137

Text #3

Max Range: 0.6445. Min Range: -0.6445

Max Act: 0.4562. Min Act: -0.0000

Data Index: 576805 (C4 (Web Text))

Max Activating Token Index: 637

Text #4

Max Range: 0.6445. Min Range: -0.6445

Max Act: 0.4655. Min Act: -0.0000

Data Index: 447457 (C4 (Web Text))

Max Activating Token Index: 411

Text #5

Max Range: 0.6445. Min Range: -0.6445

Max Act: 0.4723. Min Act: -0.0000

Data Index: 378521 (C4 (Web Text))

Max Activating Token Index: 816

Text #6

Max Range: 0.6445. Min Range: -0.6445

Max Act: 0.4421. Min Act: -0.0000

Data Index: 160159 (C4 (Web Text))

Max Activating Token Index: 471

Text #7

Max Range: 0.6445. Min Range: -0.6445

Max Act: 0.4210. Min Act: -0.0000

Data Index: 64095 (C4 (Web Text))

Max Activating Token Index: 767

Text #8

Max Range: 0.6445. Min Range: -0.6445

Max Act: 0.4558. Min Act: -0.0000

Data Index: 616512 (C4 (Web Text))

Max Activating Token Index: 556

Text #9

Max Range: 0.6445. Min Range: -0.6445

Max Act: 0.3882. Min Act: -0.0000

Data Index: 546530 (C4 (Web Text))

Max Activating Token Index: 177

Text #10

Max Range: 0.6445. Min Range: -0.6445

Max Act: 0.4253. Min Act: -0.0000

Data Index: 737496 (C4 (Web Text))

Max Activating Token Index: 462

Text #11

Max Range: 0.6445. Min Range: -0.6445

Max Act: 0.3945. Min Act: -0.0000

Data Index: 307585 (C4 (Web Text))

Max Activating Token Index: 1013

Text #12

Max Range: 0.6445. Min Range: -0.6445

Max Act: 0.3982. Min Act: -0.0000

Data Index: 63514 (C4 (Web Text))

Max Activating Token Index: 547

Text #13

Max Range: 0.6445. Min Range: -0.6445

Max Act: 0.4027. Min Act: -0.0000

Data Index: 820209 (C4 (Web Text))

Max Activating Token Index: 603

Text #14

Max Range: 0.6445. Min Range: -0.6445

Max Act: 0.4305. Min Act: -0.0000

Data Index: 33272 (C4 (Web Text))

Max Activating Token Index: 92

Text #15

Max Range: 0.6445. Min Range: -0.6445

Max Act: 0.3918. Min Act: -0.0000

Data Index: 1123440 (C4 (Web Text))

Max Activating Token Index: 345

Text #16

Max Range: 0.6445. Min Range: -0.6445

Max Act: 0.4022. Min Act: -0.0000

Data Index: 1034558 (C4 (Web Text))

Max Activating Token Index: 627

Text #17

Max Range: 0.6445. Min Range: -0.6445

Max Act: 0.3835. Min Act: -0.0000

Data Index: 281010 (C4 (Web Text))

Max Activating Token Index: 950

Text #18

Max Range: 0.6445. Min Range: -0.6445

Max Act: 0.3813. Min Act: -0.0000

Data Index: 1189489 (C4 (Web Text))

Max Activating Token Index: 503

Text #19

Max Range: 0.6445. Min Range: -0.6445

Max Act: 0.3745. Min Act: -0.0000

Data Index: 45228 (C4 (Web Text))

Max Activating Token Index: 935