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

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

Neuron 4305 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6235. Min Range: -1.6235

Max Act: 1.5951. Min Act: -0.0000

Data Index: 147521 (C4 (Web Text))

Max Activating Token Index: 588

Text #1

Max Range: 1.6235. Min Range: -1.6235

Max Act: 1.6235. Min Act: -0.0000

Data Index: 490134 (C4 (Web Text))

Max Activating Token Index: 347

Text #2

Max Range: 1.6235. Min Range: -1.6235

Max Act: 1.3189. Min Act: -0.0000

Data Index: 1176979 (C4 (Web Text))

Max Activating Token Index: 392

Text #3

Max Range: 1.6235. Min Range: -1.6235

Max Act: 1.2720. Min Act: -0.0000

Data Index: 144241 (C4 (Web Text))

Max Activating Token Index: 608

Text #4

Max Range: 1.6235. Min Range: -1.6235

Max Act: 1.2147. Min Act: -0.0000

Data Index: 517220 (C4 (Web Text))

Max Activating Token Index: 406

Text #5

Max Range: 1.6235. Min Range: -1.6235

Max Act: 0.8656. Min Act: -0.0000

Data Index: 576809 (C4 (Web Text))

Max Activating Token Index: 483

Text #6

Max Range: 1.6235. Min Range: -1.6235

Max Act: 0.8272. Min Act: -0.0000

Data Index: 786102 (C4 (Web Text))

Max Activating Token Index: 255

Text #7

Max Range: 1.6235. Min Range: -1.6235

Max Act: 0.7180. Min Act: -0.0000

Data Index: 303625 (C4 (Web Text))

Max Activating Token Index: 902

Text #8

Max Range: 1.6235. Min Range: -1.6235

Max Act: 0.7244. Min Act: -0.0000

Data Index: 1189686 (C4 (Web Text))

Max Activating Token Index: 243

Text #9

Max Range: 1.6235. Min Range: -1.6235

Max Act: 0.7285. Min Act: -0.0000

Data Index: 911320 (C4 (Web Text))

Max Activating Token Index: 506

Text #10

Max Range: 1.6235. Min Range: -1.6235

Max Act: 0.6731. Min Act: -0.0000

Data Index: 478367 (C4 (Web Text))

Max Activating Token Index: 479

Text #11

Max Range: 1.6235. Min Range: -1.6235

Max Act: 0.6157. Min Act: -0.0000

Data Index: 790957 (C4 (Web Text))

Max Activating Token Index: 896

Text #12

Max Range: 1.6235. Min Range: -1.6235

Max Act: 0.6773. Min Act: -0.0000

Data Index: 729952 (C4 (Web Text))

Max Activating Token Index: 878

Text #13

Max Range: 1.6235. Min Range: -1.6235

Max Act: 0.5930. Min Act: -0.0000

Data Index: 859387 (C4 (Web Text))

Max Activating Token Index: 903

Text #14

Max Range: 1.6235. Min Range: -1.6235

Max Act: 0.5298. Min Act: -0.0000

Data Index: 1066807 (C4 (Web Text))

Max Activating Token Index: 512

Text #15

Max Range: 1.6235. Min Range: -1.6235

Max Act: 0.6423. Min Act: -0.0000

Data Index: 303852 (C4 (Web Text))

Max Activating Token Index: 739

Text #16

Max Range: 1.6235. Min Range: -1.6235

Max Act: 0.6088. Min Act: -0.0000

Data Index: 1163343 (C4 (Web Text))

Max Activating Token Index: 406

Text #17

Max Range: 1.6235. Min Range: -1.6235

Max Act: 0.5490. Min Act: -0.0000

Data Index: 101058 (C4 (Web Text))

Max Activating Token Index: 336

Text #18

Max Range: 1.6235. Min Range: -1.6235

Max Act: 0.5850. Min Act: -0.0000

Data Index: 1290910 (C4 (Web Text))

Max Activating Token Index: 244

Text #19

Max Range: 1.6235. Min Range: -1.6235

Max Act: 0.6188. Min Act: -0.0000

Data Index: 1218216 (C4 (Web Text))

Max Activating Token Index: 452