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

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

Neuron 2000 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: 2.4504. Min Range: -2.4504

Max Act: 2.4504. Min Act: -0.0002

Data Index: 903509 (C4 (Web Text))

Max Activating Token Index: 34

Text #1

Max Range: 2.4504. Min Range: -2.4504

Max Act: 2.4200. Min Act: -0.0002

Data Index: 37763 (C4 (Web Text))

Max Activating Token Index: 19

Text #2

Max Range: 2.4504. Min Range: -2.4504

Max Act: 2.2149. Min Act: -0.0002

Data Index: 394116 (C4 (Web Text))

Max Activating Token Index: 56

Text #3

Max Range: 2.4504. Min Range: -2.4504

Max Act: 2.1748. Min Act: -0.0002

Data Index: 433966 (C4 (Web Text))

Max Activating Token Index: 304

Text #4

Max Range: 2.4504. Min Range: -2.4504

Max Act: 2.0265. Min Act: -0.0002

Data Index: 561756 (C4 (Web Text))

Max Activating Token Index: 415

Text #5

Max Range: 2.4504. Min Range: -2.4504

Max Act: 1.9991. Min Act: -0.0002

Data Index: 576679 (C4 (Web Text))

Max Activating Token Index: 279

Text #6

Max Range: 2.4504. Min Range: -2.4504

Max Act: 2.0421. Min Act: -0.0002

Data Index: 478532 (C4 (Web Text))

Max Activating Token Index: 384

Text #7

Max Range: 2.4504. Min Range: -2.4504

Max Act: 1.9886. Min Act: -0.0002

Data Index: 1217490 (C4 (Web Text))

Max Activating Token Index: 297

Text #8

Max Range: 2.4504. Min Range: -2.4504

Max Act: 1.9997. Min Act: -0.0002

Data Index: 1258634 (C4 (Web Text))

Max Activating Token Index: 126

Text #9

Max Range: 2.4504. Min Range: -2.4504

Max Act: 1.9874. Min Act: -0.0002

Data Index: 1030253 (C4 (Web Text))

Max Activating Token Index: 275

Text #10

Max Range: 2.4504. Min Range: -2.4504

Max Act: 1.9017. Min Act: -0.0002

Data Index: 780711 (C4 (Web Text))

Max Activating Token Index: 294

Text #11

Max Range: 2.4504. Min Range: -2.4504

Max Act: 1.9884. Min Act: -0.0002

Data Index: 161352 (C4 (Web Text))

Max Activating Token Index: 798

Text #12

Max Range: 2.4504. Min Range: -2.4504

Max Act: 1.9416. Min Act: -0.0002

Data Index: 1139839 (C4 (Web Text))

Max Activating Token Index: 906

Text #13

Max Range: 2.4504. Min Range: -2.4504

Max Act: 1.9629. Min Act: -0.0002

Data Index: 881823 (C4 (Web Text))

Max Activating Token Index: 832

Text #14

Max Range: 2.4504. Min Range: -2.4504

Max Act: 1.8586. Min Act: -0.0002

Data Index: 1113137 (C4 (Web Text))

Max Activating Token Index: 887

Text #15

Max Range: 2.4504. Min Range: -2.4504

Max Act: 1.8757. Min Act: -0.0002

Data Index: 255626 (C4 (Web Text))

Max Activating Token Index: 353

Text #16

Max Range: 2.4504. Min Range: -2.4504

Max Act: 1.8775. Min Act: -0.0002

Data Index: 959712 (C4 (Web Text))

Max Activating Token Index: 82

Text #17

Max Range: 2.4504. Min Range: -2.4504

Max Act: 1.9415. Min Act: -0.0002

Data Index: 428201 (C4 (Web Text))

Max Activating Token Index: 374

Text #18

Max Range: 2.4504. Min Range: -2.4504

Max Act: 1.8482. Min Act: -0.0002

Data Index: 407990 (C4 (Web Text))

Max Activating Token Index: 235

Text #19

Max Range: 2.4504. Min Range: -2.4504

Max Act: 1.9451. Min Act: -0.0002

Data Index: 874284 (C4 (Web Text))

Max Activating Token Index: 402