Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3707 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0498. Min Range: -0.0498

Max Act: 0.0498. Min Act: -0.0001

Data Index: 256965 (C4 (Web Text))

Max Activating Token Index: 557

Text #1

Max Range: 0.0498. Min Range: -0.0498

Max Act: 0.0436. Min Act: -0.0002

Data Index: 1185642 (C4 (Web Text))

Max Activating Token Index: 746

Text #2

Max Range: 0.0498. Min Range: -0.0498

Max Act: 0.0458. Min Act: -0.0002

Data Index: 23282 (C4 (Web Text))

Max Activating Token Index: 659

Text #3

Max Range: 0.0498. Min Range: -0.0498

Max Act: 0.0434. Min Act: -0.0002

Data Index: 159755 (C4 (Web Text))

Max Activating Token Index: 61

Text #4

Max Range: 0.0498. Min Range: -0.0498

Max Act: 0.0437. Min Act: -0.0002

Data Index: 1102666 (C4 (Web Text))

Max Activating Token Index: 604

Text #5

Max Range: 0.0498. Min Range: -0.0498

Max Act: 0.0461. Min Act: -0.0002

Data Index: 348393 (C4 (Web Text))

Max Activating Token Index: 785

Text #6

Max Range: 0.0498. Min Range: -0.0498

Max Act: 0.0431. Min Act: -0.0001

Data Index: 383686 (C4 (Web Text))

Max Activating Token Index: 802

Text #7

Max Range: 0.0498. Min Range: -0.0498

Max Act: 0.0412. Min Act: -0.0001

Data Index: 539009 (C4 (Web Text))

Max Activating Token Index: 232

Text #8

Max Range: 0.0498. Min Range: -0.0498

Max Act: 0.0412. Min Act: -0.0002

Data Index: 884417 (C4 (Web Text))

Max Activating Token Index: 604

Text #9

Max Range: 0.0498. Min Range: -0.0498

Max Act: 0.0386. Min Act: -0.0001

Data Index: 977241 (C4 (Web Text))

Max Activating Token Index: 326

Text #10

Max Range: 0.0498. Min Range: -0.0498

Max Act: 0.0410. Min Act: -0.0001

Data Index: 1305549 (C4 (Web Text))

Max Activating Token Index: 269

Text #11

Max Range: 0.0498. Min Range: -0.0498

Max Act: 0.0400. Min Act: -0.0002

Data Index: 427945 (C4 (Web Text))

Max Activating Token Index: 813

Text #12

Max Range: 0.0498. Min Range: -0.0498

Max Act: 0.0390. Min Act: -0.0001

Data Index: 385137 (C4 (Web Text))

Max Activating Token Index: 372

Text #13

Max Range: 0.0498. Min Range: -0.0498

Max Act: 0.0404. Min Act: -0.0001

Data Index: 1002783 (C4 (Web Text))

Max Activating Token Index: 706

Text #14

Max Range: 0.0498. Min Range: -0.0498

Max Act: 0.0379. Min Act: -0.0001

Data Index: 857237 (C4 (Web Text))

Max Activating Token Index: 532

Text #15

Max Range: 0.0498. Min Range: -0.0498

Max Act: 0.0368. Min Act: -0.0002

Data Index: 1096483 (C4 (Web Text))

Max Activating Token Index: 251

Text #16

Max Range: 0.0498. Min Range: -0.0498

Max Act: 0.0370. Min Act: -0.0002

Data Index: 1132551 (C4 (Web Text))

Max Activating Token Index: 477

Text #17

Max Range: 0.0498. Min Range: -0.0498

Max Act: 0.0373. Min Act: -0.0001

Data Index: 453349 (C4 (Web Text))

Max Activating Token Index: 475

Text #18

Max Range: 0.0498. Min Range: -0.0498

Max Act: 0.0369. Min Act: -0.0002

Data Index: 1187428 (C4 (Web Text))

Max Activating Token Index: 391

Text #19

Max Range: 0.0498. Min Range: -0.0498

Max Act: 0.0382. Min Act: -0.0002

Data Index: 1146028 (C4 (Web Text))

Max Activating Token Index: 283