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

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

Neuron 965 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0476. Min Act: -0.0006

Data Index: 1439332 (Python Code)

Max Activating Token Index: 402

Text #1

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0453. Min Act: -0.0006

Data Index: 785745 (C4 (Web Text))

Max Activating Token Index: 254

Text #2

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0449. Min Act: -0.0006

Data Index: 1517780 (Python Code)

Max Activating Token Index: 257

Text #3

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0464. Min Act: -0.0006

Data Index: 1218308 (C4 (Web Text))

Max Activating Token Index: 1002

Text #4

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0424. Min Act: -0.0006

Data Index: 656864 (C4 (Web Text))

Max Activating Token Index: 326

Text #5

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0440. Min Act: -0.0006

Data Index: 1393550 (Python Code)

Max Activating Token Index: 886

Text #6

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0417. Min Act: -0.0006

Data Index: 135050 (C4 (Web Text))

Max Activating Token Index: 279

Text #7

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0397. Min Act: -0.0006

Data Index: 155937 (C4 (Web Text))

Max Activating Token Index: 590

Text #8

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0412. Min Act: -0.0006

Data Index: 330561 (C4 (Web Text))

Max Activating Token Index: 161

Text #9

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0398. Min Act: -0.0006

Data Index: 726455 (C4 (Web Text))

Max Activating Token Index: 315

Text #10

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0406. Min Act: -0.0006

Data Index: 169537 (C4 (Web Text))

Max Activating Token Index: 337

Text #11

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0391. Min Act: -0.0006

Data Index: 326816 (C4 (Web Text))

Max Activating Token Index: 560

Text #12

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0366. Min Act: -0.0006

Data Index: 550326 (C4 (Web Text))

Max Activating Token Index: 912

Text #13

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0383. Min Act: -0.0006

Data Index: 1408762 (Python Code)

Max Activating Token Index: 310

Text #14

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0388. Min Act: -0.0006

Data Index: 115523 (C4 (Web Text))

Max Activating Token Index: 174

Text #15

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0404. Min Act: -0.0006

Data Index: 1401056 (Python Code)

Max Activating Token Index: 391

Text #16

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0378. Min Act: -0.0006

Data Index: 1373425 (Python Code)

Max Activating Token Index: 916

Text #17

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0386. Min Act: -0.0006

Data Index: 1271804 (C4 (Web Text))

Max Activating Token Index: 768

Text #18

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0376. Min Act: -0.0006

Data Index: 1576347 (Python Code)

Max Activating Token Index: 818

Text #19

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0390. Min Act: -0.0006

Data Index: 1635852 (Python Code)

Max Activating Token Index: 887