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

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

Neuron 3769 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0520. Min Range: -0.0520

Max Act: 0.0520. Min Act: -0.0000

Data Index: 1380803 (Python Code)

Max Activating Token Index: 151

Text #1

Max Range: 0.0520. Min Range: -0.0520

Max Act: 0.0485. Min Act: -0.0000

Data Index: 1434254 (Python Code)

Max Activating Token Index: 347

Text #2

Max Range: 0.0520. Min Range: -0.0520

Max Act: 0.0482. Min Act: -0.0000

Data Index: 137496 (C4 (Web Text))

Max Activating Token Index: 785

Text #3

Max Range: 0.0520. Min Range: -0.0520

Max Act: 0.0422. Min Act: -0.0000

Data Index: 1486448 (Python Code)

Max Activating Token Index: 262

Text #4

Max Range: 0.0520. Min Range: -0.0520

Max Act: 0.0451. Min Act: -0.0000

Data Index: 1513545 (Python Code)

Max Activating Token Index: 641

Text #5

Max Range: 0.0520. Min Range: -0.0520

Max Act: 0.0440. Min Act: -0.0000

Data Index: 193094 (C4 (Web Text))

Max Activating Token Index: 48

Text #6

Max Range: 0.0520. Min Range: -0.0520

Max Act: 0.0421. Min Act: -0.0000

Data Index: 1530770 (Python Code)

Max Activating Token Index: 930

Text #7

Max Range: 0.0520. Min Range: -0.0520

Max Act: 0.0434. Min Act: -0.0000

Data Index: 418812 (C4 (Web Text))

Max Activating Token Index: 353

Text #8

Max Range: 0.0520. Min Range: -0.0520

Max Act: 0.0425. Min Act: -0.0000

Data Index: 1370693 (Python Code)

Max Activating Token Index: 467

Text #9

Max Range: 0.0520. Min Range: -0.0520

Max Act: 0.0426. Min Act: -0.0000

Data Index: 1311235 (C4 (Web Text))

Max Activating Token Index: 967

Text #10

Max Range: 0.0520. Min Range: -0.0520

Max Act: 0.0433. Min Act: -0.0000

Data Index: 564831 (C4 (Web Text))

Max Activating Token Index: 490

Text #11

Max Range: 0.0520. Min Range: -0.0520

Max Act: 0.0409. Min Act: -0.0000

Data Index: 605931 (C4 (Web Text))

Max Activating Token Index: 981

Text #12

Max Range: 0.0520. Min Range: -0.0520

Max Act: 0.0406. Min Act: -0.0000

Data Index: 751339 (C4 (Web Text))

Max Activating Token Index: 44

Text #13

Max Range: 0.0520. Min Range: -0.0520

Max Act: 0.0395. Min Act: -0.0000

Data Index: 1359520 (C4 (Web Text))

Max Activating Token Index: 459

Text #14

Max Range: 0.0520. Min Range: -0.0520

Max Act: 0.0386. Min Act: -0.0000

Data Index: 400273 (C4 (Web Text))

Max Activating Token Index: 558

Text #15

Max Range: 0.0520. Min Range: -0.0520

Max Act: 0.0364. Min Act: -0.0000

Data Index: 672454 (C4 (Web Text))

Max Activating Token Index: 942

Text #16

Max Range: 0.0520. Min Range: -0.0520

Max Act: 0.0407. Min Act: -0.0000

Data Index: 4927 (C4 (Web Text))

Max Activating Token Index: 356

Text #17

Max Range: 0.0520. Min Range: -0.0520

Max Act: 0.0388. Min Act: -0.0000

Data Index: 678195 (C4 (Web Text))

Max Activating Token Index: 787

Text #18

Max Range: 0.0520. Min Range: -0.0520

Max Act: 0.0390. Min Act: -0.0000

Data Index: 1385398 (Python Code)

Max Activating Token Index: 58

Text #19

Max Range: 0.0520. Min Range: -0.0520

Max Act: 0.0405. Min Act: -0.0000

Data Index: 1605375 (Python Code)

Max Activating Token Index: 102