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

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

Neuron 2800 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2012. Min Range: -3.2012

Max Act: 3.1234. Min Act: -0.0000

Data Index: 82145 (C4 (Web Text))

Max Activating Token Index: 254

Text #1

Max Range: 3.2012. Min Range: -3.2012

Max Act: 2.9467. Min Act: -0.0000

Data Index: 590945 (C4 (Web Text))

Max Activating Token Index: 894

Text #2

Max Range: 3.2012. Min Range: -3.2012

Max Act: 2.9266. Min Act: -0.0000

Data Index: 48015 (C4 (Web Text))

Max Activating Token Index: 841

Text #3

Max Range: 3.2012. Min Range: -3.2012

Max Act: 3.2012. Min Act: -0.0000

Data Index: 777834 (C4 (Web Text))

Max Activating Token Index: 659

Text #4

Max Range: 3.2012. Min Range: -3.2012

Max Act: 3.0470. Min Act: -0.0000

Data Index: 44534 (C4 (Web Text))

Max Activating Token Index: 210

Text #5

Max Range: 3.2012. Min Range: -3.2012

Max Act: 3.0474. Min Act: -0.0000

Data Index: 140271 (C4 (Web Text))

Max Activating Token Index: 1022

Text #6

Max Range: 3.2012. Min Range: -3.2012

Max Act: 2.8957. Min Act: -0.0000

Data Index: 905701 (C4 (Web Text))

Max Activating Token Index: 169

Text #7

Max Range: 3.2012. Min Range: -3.2012

Max Act: 1.8909. Min Act: -0.0000

Data Index: 1150014 (C4 (Web Text))

Max Activating Token Index: 310

Text #8

Max Range: 3.2012. Min Range: -3.2012

Max Act: 1.8370. Min Act: -0.0000

Data Index: 676603 (C4 (Web Text))

Max Activating Token Index: 689

Text #9

Max Range: 3.2012. Min Range: -3.2012

Max Act: 2.0401. Min Act: -0.0000

Data Index: 852280 (C4 (Web Text))

Max Activating Token Index: 861

Text #10

Max Range: 3.2012. Min Range: -3.2012

Max Act: 1.7034. Min Act: -0.0000

Data Index: 273370 (C4 (Web Text))

Max Activating Token Index: 342

Text #11

Max Range: 3.2012. Min Range: -3.2012

Max Act: 1.8068. Min Act: -0.0000

Data Index: 966048 (C4 (Web Text))

Max Activating Token Index: 946

Text #12

Max Range: 3.2012. Min Range: -3.2012

Max Act: 1.8177. Min Act: -0.0000

Data Index: 540379 (C4 (Web Text))

Max Activating Token Index: 976

Text #13

Max Range: 3.2012. Min Range: -3.2012

Max Act: 2.0184. Min Act: -0.0000

Data Index: 544661 (C4 (Web Text))

Max Activating Token Index: 888

Text #14

Max Range: 3.2012. Min Range: -3.2012

Max Act: 1.9432. Min Act: -0.0000

Data Index: 602277 (C4 (Web Text))

Max Activating Token Index: 843

Text #15

Max Range: 3.2012. Min Range: -3.2012

Max Act: 1.9692. Min Act: -0.0000

Data Index: 1271995 (C4 (Web Text))

Max Activating Token Index: 464

Text #16

Max Range: 3.2012. Min Range: -3.2012

Max Act: 1.8566. Min Act: -0.0000

Data Index: 1124857 (C4 (Web Text))

Max Activating Token Index: 329

Text #17

Max Range: 3.2012. Min Range: -3.2012

Max Act: 1.8371. Min Act: -0.0000

Data Index: 937743 (C4 (Web Text))

Max Activating Token Index: 482

Text #18

Max Range: 3.2012. Min Range: -3.2012

Max Act: 1.8022. Min Act: -0.0000

Data Index: 1250020 (C4 (Web Text))

Max Activating Token Index: 419

Text #19

Max Range: 3.2012. Min Range: -3.2012

Max Act: 1.7039. Min Act: -0.0000

Data Index: 955051 (C4 (Web Text))

Max Activating Token Index: 821