Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 222 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0451. Min Range: -0.0451

Max Act: 0.0451. Min Act: -0.0005

Data Index: 582448 (C4 (Web Text))

Max Activating Token Index: 965

Text #1

Max Range: 0.0451. Min Range: -0.0451

Max Act: 0.0411. Min Act: -0.0005

Data Index: 909489 (C4 (Web Text))

Max Activating Token Index: 399

Text #2

Max Range: 0.0451. Min Range: -0.0451

Max Act: 0.0417. Min Act: -0.0005

Data Index: 500398 (C4 (Web Text))

Max Activating Token Index: 595

Text #3

Max Range: 0.0451. Min Range: -0.0451

Max Act: 0.0398. Min Act: -0.0005

Data Index: 166020 (C4 (Web Text))

Max Activating Token Index: 169

Text #4

Max Range: 0.0451. Min Range: -0.0451

Max Act: 0.0391. Min Act: -0.0005

Data Index: 263727 (C4 (Web Text))

Max Activating Token Index: 255

Text #5

Max Range: 0.0451. Min Range: -0.0451

Max Act: 0.0390. Min Act: -0.0005

Data Index: 131350 (C4 (Web Text))

Max Activating Token Index: 960

Text #6

Max Range: 0.0451. Min Range: -0.0451

Max Act: 0.0405. Min Act: -0.0004

Data Index: 1343161 (C4 (Web Text))

Max Activating Token Index: 16

Text #7

Max Range: 0.0451. Min Range: -0.0451

Max Act: 0.0376. Min Act: -0.0005

Data Index: 949851 (C4 (Web Text))

Max Activating Token Index: 747

Text #8

Max Range: 0.0451. Min Range: -0.0451

Max Act: 0.0385. Min Act: -0.0005

Data Index: 1286017 (C4 (Web Text))

Max Activating Token Index: 166

Text #9

Max Range: 0.0451. Min Range: -0.0451

Max Act: 0.0379. Min Act: -0.0005

Data Index: 1342575 (C4 (Web Text))

Max Activating Token Index: 574

Text #10

Max Range: 0.0451. Min Range: -0.0451

Max Act: 0.0382. Min Act: -0.0005

Data Index: 644917 (C4 (Web Text))

Max Activating Token Index: 919

Text #11

Max Range: 0.0451. Min Range: -0.0451

Max Act: 0.0385. Min Act: -0.0005

Data Index: 109104 (C4 (Web Text))

Max Activating Token Index: 837

Text #12

Max Range: 0.0451. Min Range: -0.0451

Max Act: 0.0373. Min Act: -0.0005

Data Index: 153789 (C4 (Web Text))

Max Activating Token Index: 1002

Text #13

Max Range: 0.0451. Min Range: -0.0451

Max Act: 0.0379. Min Act: -0.0004

Data Index: 342249 (C4 (Web Text))

Max Activating Token Index: 43

Text #14

Max Range: 0.0451. Min Range: -0.0451

Max Act: 0.0354. Min Act: -0.0005

Data Index: 1325182 (C4 (Web Text))

Max Activating Token Index: 645

Text #15

Max Range: 0.0451. Min Range: -0.0451

Max Act: 0.0376. Min Act: -0.0005

Data Index: 1358634 (C4 (Web Text))

Max Activating Token Index: 1020

Text #16

Max Range: 0.0451. Min Range: -0.0451

Max Act: 0.0368. Min Act: -0.0005

Data Index: 631835 (C4 (Web Text))

Max Activating Token Index: 736

Text #17

Max Range: 0.0451. Min Range: -0.0451

Max Act: 0.0366. Min Act: -0.0005

Data Index: 378196 (C4 (Web Text))

Max Activating Token Index: 791

Text #18

Max Range: 0.0451. Min Range: -0.0451

Max Act: 0.0363. Min Act: -0.0005

Data Index: 1343563 (C4 (Web Text))

Max Activating Token Index: 471

Text #19

Max Range: 0.0451. Min Range: -0.0451

Max Act: 0.0354. Min Act: -0.0005

Data Index: 1315742 (C4 (Web Text))

Max Activating Token Index: 635