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

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

Neuron 2772 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6452. Min Range: -0.6452

Max Act: 0.6452. Min Act: -0.0000

Data Index: 1015289 (C4 (Web Text))

Max Activating Token Index: 992

Text #1

Max Range: 0.6452. Min Range: -0.6452

Max Act: 0.6249. Min Act: -0.0000

Data Index: 955912 (C4 (Web Text))

Max Activating Token Index: 109

Text #2

Max Range: 0.6452. Min Range: -0.6452

Max Act: 0.5933. Min Act: -0.0000

Data Index: 439986 (C4 (Web Text))

Max Activating Token Index: 395

Text #3

Max Range: 0.6452. Min Range: -0.6452

Max Act: 0.5874. Min Act: -0.0000

Data Index: 900995 (C4 (Web Text))

Max Activating Token Index: 414

Text #4

Max Range: 0.6452. Min Range: -0.6452

Max Act: 0.5907. Min Act: -0.0000

Data Index: 334604 (C4 (Web Text))

Max Activating Token Index: 787

Text #5

Max Range: 0.6452. Min Range: -0.6452

Max Act: 0.5201. Min Act: -0.0000

Data Index: 874403 (C4 (Web Text))

Max Activating Token Index: 79

Text #6

Max Range: 0.6452. Min Range: -0.6452

Max Act: 0.5524. Min Act: -0.0000

Data Index: 1020049 (C4 (Web Text))

Max Activating Token Index: 998

Text #7

Max Range: 0.6452. Min Range: -0.6452

Max Act: 0.5451. Min Act: -0.0000

Data Index: 850029 (C4 (Web Text))

Max Activating Token Index: 676

Text #8

Max Range: 0.6452. Min Range: -0.6452

Max Act: 0.5885. Min Act: -0.0000

Data Index: 999525 (C4 (Web Text))

Max Activating Token Index: 952

Text #9

Max Range: 0.6452. Min Range: -0.6452

Max Act: 0.5241. Min Act: -0.0000

Data Index: 247236 (C4 (Web Text))

Max Activating Token Index: 811

Text #10

Max Range: 0.6452. Min Range: -0.6452

Max Act: 0.5397. Min Act: -0.0000

Data Index: 1044012 (C4 (Web Text))

Max Activating Token Index: 871

Text #11

Max Range: 0.6452. Min Range: -0.6452

Max Act: 0.5560. Min Act: -0.0000

Data Index: 1251230 (C4 (Web Text))

Max Activating Token Index: 328

Text #12

Max Range: 0.6452. Min Range: -0.6452

Max Act: 0.5304. Min Act: -0.0000

Data Index: 105812 (C4 (Web Text))

Max Activating Token Index: 234

Text #13

Max Range: 0.6452. Min Range: -0.6452

Max Act: 0.5197. Min Act: -0.0000

Data Index: 384570 (C4 (Web Text))

Max Activating Token Index: 937

Text #14

Max Range: 0.6452. Min Range: -0.6452

Max Act: 0.4911. Min Act: -0.0000

Data Index: 515323 (C4 (Web Text))

Max Activating Token Index: 438

Text #15

Max Range: 0.6452. Min Range: -0.6452

Max Act: 0.5612. Min Act: -0.0000

Data Index: 842094 (C4 (Web Text))

Max Activating Token Index: 389

Text #16

Max Range: 0.6452. Min Range: -0.6452

Max Act: 0.4945. Min Act: -0.0000

Data Index: 379299 (C4 (Web Text))

Max Activating Token Index: 796

Text #17

Max Range: 0.6452. Min Range: -0.6452

Max Act: 0.5285. Min Act: -0.0000

Data Index: 544829 (C4 (Web Text))

Max Activating Token Index: 760

Text #18

Max Range: 0.6452. Min Range: -0.6452

Max Act: 0.5303. Min Act: -0.0000

Data Index: 1104853 (C4 (Web Text))

Max Activating Token Index: 166

Text #19

Max Range: 0.6452. Min Range: -0.6452

Max Act: 0.4767. Min Act: -0.0000

Data Index: 5800 (C4 (Web Text))

Max Activating Token Index: 253