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

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

Neuron 1172 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0611. Min Act: -0.0000

Data Index: 1369371 (Python Code)

Max Activating Token Index: 476

Text #1

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0578. Min Act: -0.0000

Data Index: 1210540 (C4 (Web Text))

Max Activating Token Index: 726

Text #2

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0599. Min Act: -0.0000

Data Index: 703509 (C4 (Web Text))

Max Activating Token Index: 362

Text #3

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0493. Min Act: -0.0000

Data Index: 1089638 (C4 (Web Text))

Max Activating Token Index: 695

Text #4

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0516. Min Act: -0.0000

Data Index: 1177422 (C4 (Web Text))

Max Activating Token Index: 874

Text #5

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0453. Min Act: -0.0000

Data Index: 1488785 (Python Code)

Max Activating Token Index: 617

Text #6

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0469. Min Act: -0.0000

Data Index: 394812 (C4 (Web Text))

Max Activating Token Index: 397

Text #7

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0436. Min Act: -0.0000

Data Index: 1043435 (C4 (Web Text))

Max Activating Token Index: 497

Text #8

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0443. Min Act: -0.0000

Data Index: 553776 (C4 (Web Text))

Max Activating Token Index: 36

Text #9

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0410. Min Act: -0.0000

Data Index: 1407544 (Python Code)

Max Activating Token Index: 418

Text #10

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0477. Min Act: -0.0000

Data Index: 422498 (C4 (Web Text))

Max Activating Token Index: 392

Text #11

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0413. Min Act: -0.0000

Data Index: 1483901 (Python Code)

Max Activating Token Index: 462

Text #12

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0407. Min Act: -0.0000

Data Index: 1238229 (C4 (Web Text))

Max Activating Token Index: 978

Text #13

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0376. Min Act: -0.0000

Data Index: 1192033 (C4 (Web Text))

Max Activating Token Index: 378

Text #14

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0420. Min Act: -0.0000

Data Index: 427292 (C4 (Web Text))

Max Activating Token Index: 257

Text #15

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0416. Min Act: -0.0000

Data Index: 958889 (C4 (Web Text))

Max Activating Token Index: 40

Text #16

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0445. Min Act: -0.0000

Data Index: 1488522 (Python Code)

Max Activating Token Index: 826

Text #17

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0462. Min Act: -0.0000

Data Index: 229852 (C4 (Web Text))

Max Activating Token Index: 1010

Text #18

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0408. Min Act: -0.0000

Data Index: 886902 (C4 (Web Text))

Max Activating Token Index: 1006

Text #19

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0394. Min Act: -0.0000

Data Index: 250156 (C4 (Web Text))

Max Activating Token Index: 325