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

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

Neuron 3864 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: 0.8876. Min Range: -0.8876

Max Act: 0.8876. Min Act: -0.0002

Data Index: 1129549 (C4 (Web Text))

Max Activating Token Index: 232

Text #1

Max Range: 0.8876. Min Range: -0.8876

Max Act: 0.8273. Min Act: -0.0002

Data Index: 1071848 (C4 (Web Text))

Max Activating Token Index: 226

Text #2

Max Range: 0.8876. Min Range: -0.8876

Max Act: 0.8229. Min Act: -0.0002

Data Index: 725298 (C4 (Web Text))

Max Activating Token Index: 50

Text #3

Max Range: 0.8876. Min Range: -0.8876

Max Act: 0.8039. Min Act: -0.0003

Data Index: 544427 (C4 (Web Text))

Max Activating Token Index: 124

Text #4

Max Range: 0.8876. Min Range: -0.8876

Max Act: 0.7598. Min Act: -0.0002

Data Index: 378388 (C4 (Web Text))

Max Activating Token Index: 550

Text #5

Max Range: 0.8876. Min Range: -0.8876

Max Act: 0.7509. Min Act: -0.0003

Data Index: 743402 (C4 (Web Text))

Max Activating Token Index: 985

Text #6

Max Range: 0.8876. Min Range: -0.8876

Max Act: 0.7656. Min Act: -0.0002

Data Index: 1147899 (C4 (Web Text))

Max Activating Token Index: 381

Text #7

Max Range: 0.8876. Min Range: -0.8876

Max Act: 0.7471. Min Act: -0.0003

Data Index: 1273693 (C4 (Web Text))

Max Activating Token Index: 610

Text #8

Max Range: 0.8876. Min Range: -0.8876

Max Act: 0.7347. Min Act: -0.0002

Data Index: 363754 (C4 (Web Text))

Max Activating Token Index: 56

Text #9

Max Range: 0.8876. Min Range: -0.8876

Max Act: 0.7169. Min Act: -0.0002

Data Index: 586305 (C4 (Web Text))

Max Activating Token Index: 151

Text #10

Max Range: 0.8876. Min Range: -0.8876

Max Act: 0.7068. Min Act: -0.0002

Data Index: 557385 (C4 (Web Text))

Max Activating Token Index: 89

Text #11

Max Range: 0.8876. Min Range: -0.8876

Max Act: 0.7038. Min Act: -0.0003

Data Index: 508278 (C4 (Web Text))

Max Activating Token Index: 92

Text #12

Max Range: 0.8876. Min Range: -0.8876

Max Act: 0.7067. Min Act: -0.0002

Data Index: 308871 (C4 (Web Text))

Max Activating Token Index: 772

Text #13

Max Range: 0.8876. Min Range: -0.8876

Max Act: 0.6864. Min Act: -0.0002

Data Index: 725202 (C4 (Web Text))

Max Activating Token Index: 397

Text #14

Max Range: 0.8876. Min Range: -0.8876

Max Act: 0.6825. Min Act: -0.0003

Data Index: 1288553 (C4 (Web Text))

Max Activating Token Index: 526

Text #15

Max Range: 0.8876. Min Range: -0.8876

Max Act: 0.6770. Min Act: -0.0003

Data Index: 395315 (C4 (Web Text))

Max Activating Token Index: 946

Text #16

Max Range: 0.8876. Min Range: -0.8876

Max Act: 0.6878. Min Act: -0.0002

Data Index: 1009631 (C4 (Web Text))

Max Activating Token Index: 873

Text #17

Max Range: 0.8876. Min Range: -0.8876

Max Act: 0.6504. Min Act: -0.0003

Data Index: 162889 (C4 (Web Text))

Max Activating Token Index: 307

Text #18

Max Range: 0.8876. Min Range: -0.8876

Max Act: 0.6574. Min Act: -0.0002

Data Index: 414408 (C4 (Web Text))

Max Activating Token Index: 886

Text #19

Max Range: 0.8876. Min Range: -0.8876

Max Act: 0.6586. Min Act: -0.0003

Data Index: 727228 (C4 (Web Text))

Max Activating Token Index: 504