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

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

Neuron 1250 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4546. Min Range: -0.4546

Max Act: 0.4460. Min Act: -0.0000

Data Index: 361365 (C4 (Web Text))

Max Activating Token Index: 711

Text #1

Max Range: 0.4546. Min Range: -0.4546

Max Act: 0.4546. Min Act: -0.0000

Data Index: 845782 (C4 (Web Text))

Max Activating Token Index: 936

Text #2

Max Range: 0.4546. Min Range: -0.4546

Max Act: 0.4452. Min Act: -0.0000

Data Index: 125957 (C4 (Web Text))

Max Activating Token Index: 842

Text #3

Max Range: 0.4546. Min Range: -0.4546

Max Act: 0.4411. Min Act: -0.0000

Data Index: 1009017 (C4 (Web Text))

Max Activating Token Index: 488

Text #4

Max Range: 0.4546. Min Range: -0.4546

Max Act: 0.4273. Min Act: -0.0000

Data Index: 1306324 (C4 (Web Text))

Max Activating Token Index: 495

Text #5

Max Range: 0.4546. Min Range: -0.4546

Max Act: 0.3725. Min Act: -0.0000

Data Index: 1109132 (C4 (Web Text))

Max Activating Token Index: 838

Text #6

Max Range: 0.4546. Min Range: -0.4546

Max Act: 0.3640. Min Act: -0.0000

Data Index: 1029943 (C4 (Web Text))

Max Activating Token Index: 403

Text #7

Max Range: 0.4546. Min Range: -0.4546

Max Act: 0.3679. Min Act: -0.0000

Data Index: 112287 (C4 (Web Text))

Max Activating Token Index: 745

Text #8

Max Range: 0.4546. Min Range: -0.4546

Max Act: 0.3474. Min Act: -0.0000

Data Index: 399526 (C4 (Web Text))

Max Activating Token Index: 681

Text #9

Max Range: 0.4546. Min Range: -0.4546

Max Act: 0.3364. Min Act: -0.0000

Data Index: 1084298 (C4 (Web Text))

Max Activating Token Index: 450

Text #10

Max Range: 0.4546. Min Range: -0.4546

Max Act: 0.3359. Min Act: -0.0000

Data Index: 157853 (C4 (Web Text))

Max Activating Token Index: 775

Text #11

Max Range: 0.4546. Min Range: -0.4546

Max Act: 0.3389. Min Act: -0.0000

Data Index: 560656 (C4 (Web Text))

Max Activating Token Index: 713

Text #12

Max Range: 0.4546. Min Range: -0.4546

Max Act: 0.3258. Min Act: -0.0000

Data Index: 349090 (C4 (Web Text))

Max Activating Token Index: 49

Text #13

Max Range: 0.4546. Min Range: -0.4546

Max Act: 0.3183. Min Act: -0.0000

Data Index: 240206 (C4 (Web Text))

Max Activating Token Index: 386

Text #14

Max Range: 0.4546. Min Range: -0.4546

Max Act: 0.3072. Min Act: -0.0000

Data Index: 1166803 (C4 (Web Text))

Max Activating Token Index: 812

Text #15

Max Range: 0.4546. Min Range: -0.4546

Max Act: 0.3028. Min Act: -0.0000

Data Index: 696332 (C4 (Web Text))

Max Activating Token Index: 707

Text #16

Max Range: 0.4546. Min Range: -0.4546

Max Act: 0.3024. Min Act: -0.0000

Data Index: 923236 (C4 (Web Text))

Max Activating Token Index: 480

Text #17

Max Range: 0.4546. Min Range: -0.4546

Max Act: 0.3030. Min Act: -0.0000

Data Index: 982085 (C4 (Web Text))

Max Activating Token Index: 676

Text #18

Max Range: 0.4546. Min Range: -0.4546

Max Act: 0.3075. Min Act: -0.0000

Data Index: 965525 (C4 (Web Text))

Max Activating Token Index: 450

Text #19

Max Range: 0.4546. Min Range: -0.4546

Max Act: 0.3087. Min Act: -0.0000

Data Index: 173415 (C4 (Web Text))

Max Activating Token Index: 358