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

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

Neuron 640 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: 1.2015. Min Range: -1.2015

Max Act: 1.1808. Min Act: 0.0001

Data Index: 10064 (C4 (Web Text))

Max Activating Token Index: 320

Text #1

Max Range: 1.2015. Min Range: -1.2015

Max Act: 1.2015. Min Act: -0.0000

Data Index: 1015112 (C4 (Web Text))

Max Activating Token Index: 370

Text #2

Max Range: 1.2015. Min Range: -1.2015

Max Act: 1.1566. Min Act: -0.0000

Data Index: 186358 (C4 (Web Text))

Max Activating Token Index: 971

Text #3

Max Range: 1.2015. Min Range: -1.2015

Max Act: 1.0801. Min Act: -0.0000

Data Index: 705289 (C4 (Web Text))

Max Activating Token Index: 179

Text #4

Max Range: 1.2015. Min Range: -1.2015

Max Act: 1.0917. Min Act: 0.0000

Data Index: 571451 (C4 (Web Text))

Max Activating Token Index: 598

Text #5

Max Range: 1.2015. Min Range: -1.2015

Max Act: 1.0984. Min Act: 0.0000

Data Index: 1036871 (C4 (Web Text))

Max Activating Token Index: 912

Text #6

Max Range: 1.2015. Min Range: -1.2015

Max Act: 1.0887. Min Act: -0.0000

Data Index: 1059303 (C4 (Web Text))

Max Activating Token Index: 685

Text #7

Max Range: 1.2015. Min Range: -1.2015

Max Act: 1.0357. Min Act: -0.0000

Data Index: 1333526 (C4 (Web Text))

Max Activating Token Index: 943

Text #8

Max Range: 1.2015. Min Range: -1.2015

Max Act: 1.0415. Min Act: -0.0000

Data Index: 6303 (C4 (Web Text))

Max Activating Token Index: 288

Text #9

Max Range: 1.2015. Min Range: -1.2015

Max Act: 1.0065. Min Act: -0.0000

Data Index: 32962 (C4 (Web Text))

Max Activating Token Index: 447

Text #10

Max Range: 1.2015. Min Range: -1.2015

Max Act: 0.9927. Min Act: -0.0000

Data Index: 946058 (C4 (Web Text))

Max Activating Token Index: 254

Text #11

Max Range: 1.2015. Min Range: -1.2015

Max Act: 0.9847. Min Act: -0.0000

Data Index: 579903 (C4 (Web Text))

Max Activating Token Index: 49

Text #12

Max Range: 1.2015. Min Range: -1.2015

Max Act: 0.9676. Min Act: -0.0000

Data Index: 406968 (C4 (Web Text))

Max Activating Token Index: 233

Text #13

Max Range: 1.2015. Min Range: -1.2015

Max Act: 0.9654. Min Act: -0.0000

Data Index: 889485 (C4 (Web Text))

Max Activating Token Index: 903

Text #14

Max Range: 1.2015. Min Range: -1.2015

Max Act: 1.0024. Min Act: -0.0000

Data Index: 990033 (C4 (Web Text))

Max Activating Token Index: 1005

Text #15

Max Range: 1.2015. Min Range: -1.2015

Max Act: 0.9407. Min Act: -0.0000

Data Index: 1015578 (C4 (Web Text))

Max Activating Token Index: 628

Text #16

Max Range: 1.2015. Min Range: -1.2015

Max Act: 0.9900. Min Act: -0.0000

Data Index: 470785 (C4 (Web Text))

Max Activating Token Index: 324

Text #17

Max Range: 1.2015. Min Range: -1.2015

Max Act: 0.9319. Min Act: -0.0000

Data Index: 840614 (C4 (Web Text))

Max Activating Token Index: 995

Text #18

Max Range: 1.2015. Min Range: -1.2015

Max Act: 0.8233. Min Act: -0.0000

Data Index: 285931 (C4 (Web Text))

Max Activating Token Index: 786

Text #19

Max Range: 1.2015. Min Range: -1.2015

Max Act: 0.9208. Min Act: -0.0000

Data Index: 660233 (C4 (Web Text))

Max Activating Token Index: 860