Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1298 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.4326. Min Range: -0.4326

Max Act: 0.4326. Min Act: -0.0002

Data Index: 1057612 (C4 (Web Text))

Max Activating Token Index: 3

Text #1

Max Range: 0.4326. Min Range: -0.4326

Max Act: 0.3877. Min Act: -0.0002

Data Index: 90854 (C4 (Web Text))

Max Activating Token Index: 592

Text #2

Max Range: 0.4326. Min Range: -0.4326

Max Act: 0.3812. Min Act: -0.0002

Data Index: 981996 (C4 (Web Text))

Max Activating Token Index: 8

Text #3

Max Range: 0.4326. Min Range: -0.4326

Max Act: 0.3849. Min Act: -0.0002

Data Index: 1334386 (C4 (Web Text))

Max Activating Token Index: 2

Text #4

Max Range: 0.4326. Min Range: -0.4326

Max Act: 0.3849. Min Act: -0.0002

Data Index: 1189399 (C4 (Web Text))

Max Activating Token Index: 2

Text #5

Max Range: 0.4326. Min Range: -0.4326

Max Act: 0.3849. Min Act: -0.0002

Data Index: 32228 (C4 (Web Text))

Max Activating Token Index: 2

Text #6

Max Range: 0.4326. Min Range: -0.4326

Max Act: 0.3845. Min Act: -0.0002

Data Index: 585457 (C4 (Web Text))

Max Activating Token Index: 12

Text #7

Max Range: 0.4326. Min Range: -0.4326

Max Act: 0.3743. Min Act: -0.0002

Data Index: 1139823 (C4 (Web Text))

Max Activating Token Index: 26

Text #8

Max Range: 0.4326. Min Range: -0.4326

Max Act: 0.3698. Min Act: -0.0002

Data Index: 1340595 (C4 (Web Text))

Max Activating Token Index: 20

Text #9

Max Range: 0.4326. Min Range: -0.4326

Max Act: 0.3700. Min Act: -0.0002

Data Index: 661181 (C4 (Web Text))

Max Activating Token Index: 79

Text #10

Max Range: 0.4326. Min Range: -0.4326

Max Act: 0.3632. Min Act: -0.0002

Data Index: 910169 (C4 (Web Text))

Max Activating Token Index: 607

Text #11

Max Range: 0.4326. Min Range: -0.4326

Max Act: 0.3544. Min Act: -0.0002

Data Index: 444190 (C4 (Web Text))

Max Activating Token Index: 902

Text #12

Max Range: 0.4326. Min Range: -0.4326

Max Act: 0.3503. Min Act: -0.0002

Data Index: 864393 (C4 (Web Text))

Max Activating Token Index: 126

Text #13

Max Range: 0.4326. Min Range: -0.4326

Max Act: 0.3592. Min Act: -0.0002

Data Index: 1279986 (C4 (Web Text))

Max Activating Token Index: 5

Text #14

Max Range: 0.4326. Min Range: -0.4326

Max Act: 0.3460. Min Act: -0.0002

Data Index: 830707 (C4 (Web Text))

Max Activating Token Index: 825

Text #15

Max Range: 0.4326. Min Range: -0.4326

Max Act: 0.3558. Min Act: -0.0002

Data Index: 851045 (C4 (Web Text))

Max Activating Token Index: 858

Text #16

Max Range: 0.4326. Min Range: -0.4326

Max Act: 0.3476. Min Act: -0.0002

Data Index: 894884 (C4 (Web Text))

Max Activating Token Index: 746

Text #17

Max Range: 0.4326. Min Range: -0.4326

Max Act: 0.3465. Min Act: -0.0002

Data Index: 98310 (C4 (Web Text))

Max Activating Token Index: 230

Text #18

Max Range: 0.4326. Min Range: -0.4326

Max Act: 0.3400. Min Act: -0.0002

Data Index: 1271340 (C4 (Web Text))

Max Activating Token Index: 722

Text #19

Max Range: 0.4326. Min Range: -0.4326

Max Act: 0.3354. Min Act: -0.0002

Data Index: 616568 (C4 (Web Text))

Max Activating Token Index: 52