Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1176 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0430. Min Act: -0.0006

Data Index: 1233978 (C4 (Web Text))

Max Activating Token Index: 238

Text #1

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0428. Min Act: -0.0006

Data Index: 111725 (C4 (Web Text))

Max Activating Token Index: 772

Text #2

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0441. Min Act: -0.0006

Data Index: 424291 (C4 (Web Text))

Max Activating Token Index: 22

Text #3

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0420. Min Act: -0.0006

Data Index: 971893 (C4 (Web Text))

Max Activating Token Index: 297

Text #4

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0407. Min Act: -0.0006

Data Index: 60557 (C4 (Web Text))

Max Activating Token Index: 971

Text #5

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0404. Min Act: -0.0006

Data Index: 453268 (C4 (Web Text))

Max Activating Token Index: 932

Text #6

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0391. Min Act: -0.0006

Data Index: 122960 (C4 (Web Text))

Max Activating Token Index: 465

Text #7

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0346. Min Act: -0.0006

Data Index: 1274348 (C4 (Web Text))

Max Activating Token Index: 662

Text #8

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0403. Min Act: -0.0005

Data Index: 540000 (C4 (Web Text))

Max Activating Token Index: 739

Text #9

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0399. Min Act: -0.0006

Data Index: 186705 (C4 (Web Text))

Max Activating Token Index: 926

Text #10

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0394. Min Act: -0.0006

Data Index: 348631 (C4 (Web Text))

Max Activating Token Index: 859

Text #11

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0388. Min Act: -0.0006

Data Index: 977806 (C4 (Web Text))

Max Activating Token Index: 578

Text #12

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0379. Min Act: -0.0006

Data Index: 1313129 (C4 (Web Text))

Max Activating Token Index: 716

Text #13

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0381. Min Act: -0.0006

Data Index: 1253559 (C4 (Web Text))

Max Activating Token Index: 886

Text #14

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0404. Min Act: -0.0006

Data Index: 829221 (C4 (Web Text))

Max Activating Token Index: 641

Text #15

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0376. Min Act: -0.0006

Data Index: 1088380 (C4 (Web Text))

Max Activating Token Index: 914

Text #16

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0359. Min Act: -0.0006

Data Index: 355632 (C4 (Web Text))

Max Activating Token Index: 760

Text #17

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0377. Min Act: -0.0006

Data Index: 603909 (C4 (Web Text))

Max Activating Token Index: 710

Text #18

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0392. Min Act: -0.0006

Data Index: 1085633 (C4 (Web Text))

Max Activating Token Index: 357

Text #19

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0371. Min Act: -0.0006

Data Index: 628551 (C4 (Web Text))

Max Activating Token Index: 644