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

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

Neuron 2274 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0487. Min Act: -0.0000

Data Index: 230053 (C4 (Web Text))

Max Activating Token Index: 359

Text #1

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0510. Min Act: -0.0000

Data Index: 552856 (C4 (Web Text))

Max Activating Token Index: 685

Text #2

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0482. Min Act: -0.0000

Data Index: 16408 (C4 (Web Text))

Max Activating Token Index: 898

Text #3

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0449. Min Act: -0.0000

Data Index: 1058091 (C4 (Web Text))

Max Activating Token Index: 476

Text #4

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0466. Min Act: -0.0000

Data Index: 554432 (C4 (Web Text))

Max Activating Token Index: 356

Text #5

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0423. Min Act: -0.0000

Data Index: 405611 (C4 (Web Text))

Max Activating Token Index: 38

Text #6

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0425. Min Act: -0.0000

Data Index: 250988 (C4 (Web Text))

Max Activating Token Index: 388

Text #7

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0428. Min Act: -0.0000

Data Index: 187572 (C4 (Web Text))

Max Activating Token Index: 535

Text #8

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0432. Min Act: -0.0000

Data Index: 490317 (C4 (Web Text))

Max Activating Token Index: 707

Text #9

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0424. Min Act: -0.0000

Data Index: 175342 (C4 (Web Text))

Max Activating Token Index: 100

Text #10

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0419. Min Act: -0.0000

Data Index: 1347077 (C4 (Web Text))

Max Activating Token Index: 736

Text #11

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0432. Min Act: -0.0000

Data Index: 269558 (C4 (Web Text))

Max Activating Token Index: 946

Text #12

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0372. Min Act: -0.0000

Data Index: 381758 (C4 (Web Text))

Max Activating Token Index: 81

Text #13

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0386. Min Act: -0.0000

Data Index: 1507239 (Python Code)

Max Activating Token Index: 159

Text #14

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0411. Min Act: -0.0000

Data Index: 970184 (C4 (Web Text))

Max Activating Token Index: 890

Text #15

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0368. Min Act: -0.0000

Data Index: 510283 (C4 (Web Text))

Max Activating Token Index: 616

Text #16

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0409. Min Act: -0.0000

Data Index: 201877 (C4 (Web Text))

Max Activating Token Index: 727

Text #17

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0393. Min Act: -0.0000

Data Index: 1075525 (C4 (Web Text))

Max Activating Token Index: 460

Text #18

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0382. Min Act: -0.0000

Data Index: 1062638 (C4 (Web Text))

Max Activating Token Index: 190

Text #19

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0402. Min Act: -0.0000

Data Index: 879517 (C4 (Web Text))

Max Activating Token Index: 943