Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 688 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0621. Min Act: -0.0000

Data Index: 1261345 (C4 (Web Text))

Max Activating Token Index: 378

Text #1

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0592. Min Act: -0.0000

Data Index: 749944 (C4 (Web Text))

Max Activating Token Index: 539

Text #2

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0491. Min Act: -0.0000

Data Index: 394354 (C4 (Web Text))

Max Activating Token Index: 99

Text #3

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0490. Min Act: -0.0000

Data Index: 1056294 (C4 (Web Text))

Max Activating Token Index: 452

Text #4

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0476. Min Act: -0.0000

Data Index: 1024588 (C4 (Web Text))

Max Activating Token Index: 633

Text #5

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0445. Min Act: -0.0000

Data Index: 25200 (C4 (Web Text))

Max Activating Token Index: 667

Text #6

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0417. Min Act: -0.0000

Data Index: 422214 (C4 (Web Text))

Max Activating Token Index: 442

Text #7

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0403. Min Act: -0.0000

Data Index: 927645 (C4 (Web Text))

Max Activating Token Index: 700

Text #8

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0403. Min Act: -0.0000

Data Index: 740646 (C4 (Web Text))

Max Activating Token Index: 396

Text #9

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0399. Min Act: 0.0000

Data Index: 1110340 (C4 (Web Text))

Max Activating Token Index: 52

Text #10

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0425. Min Act: -0.0000

Data Index: 1441766 (Python Code)

Max Activating Token Index: 313

Text #11

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0393. Min Act: -0.0000

Data Index: 1225937 (C4 (Web Text))

Max Activating Token Index: 349

Text #12

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0408. Min Act: -0.0000

Data Index: 630266 (C4 (Web Text))

Max Activating Token Index: 895

Text #13

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0402. Min Act: 0.0000

Data Index: 1076487 (C4 (Web Text))

Max Activating Token Index: 558

Text #14

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0392. Min Act: -0.0000

Data Index: 594052 (C4 (Web Text))

Max Activating Token Index: 946

Text #15

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0391. Min Act: -0.0000

Data Index: 405640 (C4 (Web Text))

Max Activating Token Index: 383

Text #16

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0382. Min Act: -0.0000

Data Index: 1441724 (Python Code)

Max Activating Token Index: 1003

Text #17

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0367. Min Act: -0.0000

Data Index: 593792 (C4 (Web Text))

Max Activating Token Index: 272

Text #18

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0380. Min Act: -0.0000

Data Index: 713713 (C4 (Web Text))

Max Activating Token Index: 632

Text #19

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0379. Min Act: -0.0000

Data Index: 818048 (C4 (Web Text))

Max Activating Token Index: 66