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

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

Neuron 1252 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: 0.7343. Min Range: -0.7343

Max Act: 0.7343. Min Act: -0.0002

Data Index: 1049064 (C4 (Web Text))

Max Activating Token Index: 735

Text #1

Max Range: 0.7343. Min Range: -0.7343

Max Act: 0.6903. Min Act: -0.0002

Data Index: 827432 (C4 (Web Text))

Max Activating Token Index: 167

Text #2

Max Range: 0.7343. Min Range: -0.7343

Max Act: 0.6805. Min Act: -0.0002

Data Index: 1267405 (C4 (Web Text))

Max Activating Token Index: 659

Text #3

Max Range: 0.7343. Min Range: -0.7343

Max Act: 0.6796. Min Act: -0.0002

Data Index: 1046529 (C4 (Web Text))

Max Activating Token Index: 211

Text #4

Max Range: 0.7343. Min Range: -0.7343

Max Act: 0.6859. Min Act: -0.0002

Data Index: 791001 (C4 (Web Text))

Max Activating Token Index: 532

Text #5

Max Range: 0.7343. Min Range: -0.7343

Max Act: 0.6720. Min Act: -0.0002

Data Index: 1038720 (C4 (Web Text))

Max Activating Token Index: 127

Text #6

Max Range: 0.7343. Min Range: -0.7343

Max Act: 0.6642. Min Act: -0.0002

Data Index: 1144213 (C4 (Web Text))

Max Activating Token Index: 400

Text #7

Max Range: 0.7343. Min Range: -0.7343

Max Act: 0.6782. Min Act: -0.0002

Data Index: 1038861 (C4 (Web Text))

Max Activating Token Index: 270

Text #8

Max Range: 0.7343. Min Range: -0.7343

Max Act: 0.6656. Min Act: -0.0002

Data Index: 1127879 (C4 (Web Text))

Max Activating Token Index: 293

Text #9

Max Range: 0.7343. Min Range: -0.7343

Max Act: 0.6617. Min Act: -0.0003

Data Index: 1054296 (C4 (Web Text))

Max Activating Token Index: 831

Text #10

Max Range: 0.7343. Min Range: -0.7343

Max Act: 0.6418. Min Act: -0.0002

Data Index: 196438 (C4 (Web Text))

Max Activating Token Index: 720

Text #11

Max Range: 0.7343. Min Range: -0.7343

Max Act: 0.6601. Min Act: -0.0002

Data Index: 793534 (C4 (Web Text))

Max Activating Token Index: 170

Text #12

Max Range: 0.7343. Min Range: -0.7343

Max Act: 0.6444. Min Act: -0.0002

Data Index: 957365 (C4 (Web Text))

Max Activating Token Index: 3

Text #13

Max Range: 0.7343. Min Range: -0.7343

Max Act: 0.6478. Min Act: -0.0002

Data Index: 681490 (C4 (Web Text))

Max Activating Token Index: 653

Text #14

Max Range: 0.7343. Min Range: -0.7343

Max Act: 0.6407. Min Act: -0.0002

Data Index: 231364 (C4 (Web Text))

Max Activating Token Index: 266

Text #15

Max Range: 0.7343. Min Range: -0.7343

Max Act: 0.6340. Min Act: -0.0002

Data Index: 979130 (C4 (Web Text))

Max Activating Token Index: 203

Text #16

Max Range: 0.7343. Min Range: -0.7343

Max Act: 0.6355. Min Act: -0.0003

Data Index: 591014 (C4 (Web Text))

Max Activating Token Index: 468

Text #17

Max Range: 0.7343. Min Range: -0.7343

Max Act: 0.6312. Min Act: -0.0003

Data Index: 1123147 (C4 (Web Text))

Max Activating Token Index: 83

Text #18

Max Range: 0.7343. Min Range: -0.7343

Max Act: 0.6356. Min Act: -0.0003

Data Index: 852147 (C4 (Web Text))

Max Activating Token Index: 967

Text #19

Max Range: 0.7343. Min Range: -0.7343

Max Act: 0.6269. Min Act: -0.0002

Data Index: 725638 (C4 (Web Text))

Max Activating Token Index: 8