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

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

Neuron 3091 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5555. Min Range: -1.5555

Max Act: 1.5555. Min Act: -0.0000

Data Index: 888236 (C4 (Web Text))

Max Activating Token Index: 734

Text #1

Max Range: 1.5555. Min Range: -1.5555

Max Act: 1.3947. Min Act: -0.0000

Data Index: 166542 (C4 (Web Text))

Max Activating Token Index: 100

Text #2

Max Range: 1.5555. Min Range: -1.5555

Max Act: 1.2012. Min Act: -0.0000

Data Index: 215412 (C4 (Web Text))

Max Activating Token Index: 484

Text #3

Max Range: 1.5555. Min Range: -1.5555

Max Act: 1.1647. Min Act: -0.0000

Data Index: 394997 (C4 (Web Text))

Max Activating Token Index: 819

Text #4

Max Range: 1.5555. Min Range: -1.5555

Max Act: 1.1536. Min Act: -0.0000

Data Index: 893282 (C4 (Web Text))

Max Activating Token Index: 859

Text #5

Max Range: 1.5555. Min Range: -1.5555

Max Act: 0.9830. Min Act: -0.0000

Data Index: 350546 (C4 (Web Text))

Max Activating Token Index: 178

Text #6

Max Range: 1.5555. Min Range: -1.5555

Max Act: 1.0311. Min Act: -0.0000

Data Index: 854392 (C4 (Web Text))

Max Activating Token Index: 581

Text #7

Max Range: 1.5555. Min Range: -1.5555

Max Act: 0.9010. Min Act: -0.0000

Data Index: 940900 (C4 (Web Text))

Max Activating Token Index: 136

Text #8

Max Range: 1.5555. Min Range: -1.5555

Max Act: 0.9945. Min Act: -0.0000

Data Index: 280880 (C4 (Web Text))

Max Activating Token Index: 458

Text #9

Max Range: 1.5555. Min Range: -1.5555

Max Act: 0.9937. Min Act: -0.0000

Data Index: 265843 (C4 (Web Text))

Max Activating Token Index: 589

Text #10

Max Range: 1.5555. Min Range: -1.5555

Max Act: 0.9517. Min Act: -0.0000

Data Index: 222737 (C4 (Web Text))

Max Activating Token Index: 471

Text #11

Max Range: 1.5555. Min Range: -1.5555

Max Act: 0.8978. Min Act: -0.0000

Data Index: 269609 (C4 (Web Text))

Max Activating Token Index: 421

Text #12

Max Range: 1.5555. Min Range: -1.5555

Max Act: 0.8507. Min Act: -0.0000

Data Index: 821818 (C4 (Web Text))

Max Activating Token Index: 891

Text #13

Max Range: 1.5555. Min Range: -1.5555

Max Act: 0.8014. Min Act: -0.0000

Data Index: 104147 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 1.5555. Min Range: -1.5555

Max Act: 0.8200. Min Act: -0.0000

Data Index: 1189590 (C4 (Web Text))

Max Activating Token Index: 276

Text #15

Max Range: 1.5555. Min Range: -1.5555

Max Act: 0.8332. Min Act: -0.0000

Data Index: 452767 (C4 (Web Text))

Max Activating Token Index: 983

Text #16

Max Range: 1.5555. Min Range: -1.5555

Max Act: 0.8167. Min Act: -0.0000

Data Index: 1064521 (C4 (Web Text))

Max Activating Token Index: 648

Text #17

Max Range: 1.5555. Min Range: -1.5555

Max Act: 0.8422. Min Act: -0.0000

Data Index: 221238 (C4 (Web Text))

Max Activating Token Index: 637

Text #18

Max Range: 1.5555. Min Range: -1.5555

Max Act: 0.7317. Min Act: -0.0000

Data Index: 707952 (C4 (Web Text))

Max Activating Token Index: 242

Text #19

Max Range: 1.5555. Min Range: -1.5555

Max Act: 0.8154. Min Act: -0.0000

Data Index: 668868 (C4 (Web Text))

Max Activating Token Index: 883