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

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

Neuron 1454 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2702. Min Range: -0.2702

Max Act: 0.2246. Min Act: -0.0001

Data Index: 784523 (C4 (Web Text))

Max Activating Token Index: 715

Text #1

Max Range: 0.2702. Min Range: -0.2702

Max Act: 0.2702. Min Act: -0.0001

Data Index: 982192 (C4 (Web Text))

Max Activating Token Index: 748

Text #2

Max Range: 0.2702. Min Range: -0.2702

Max Act: 0.2667. Min Act: -0.0001

Data Index: 27564 (C4 (Web Text))

Max Activating Token Index: 800

Text #3

Max Range: 0.2702. Min Range: -0.2702

Max Act: 0.2659. Min Act: -0.0001

Data Index: 38511 (C4 (Web Text))

Max Activating Token Index: 570

Text #4

Max Range: 0.2702. Min Range: -0.2702

Max Act: 0.2512. Min Act: -0.0001

Data Index: 703339 (C4 (Web Text))

Max Activating Token Index: 117

Text #5

Max Range: 0.2702. Min Range: -0.2702

Max Act: 0.2458. Min Act: -0.0001

Data Index: 1228858 (C4 (Web Text))

Max Activating Token Index: 559

Text #6

Max Range: 0.2702. Min Range: -0.2702

Max Act: 0.2561. Min Act: -0.0001

Data Index: 344127 (C4 (Web Text))

Max Activating Token Index: 205

Text #7

Max Range: 0.2702. Min Range: -0.2702

Max Act: 0.2478. Min Act: -0.0001

Data Index: 671825 (C4 (Web Text))

Max Activating Token Index: 788

Text #8

Max Range: 0.2702. Min Range: -0.2702

Max Act: 0.2479. Min Act: -0.0001

Data Index: 976093 (C4 (Web Text))

Max Activating Token Index: 339

Text #9

Max Range: 0.2702. Min Range: -0.2702

Max Act: 0.2294. Min Act: -0.0001

Data Index: 17745 (C4 (Web Text))

Max Activating Token Index: 169

Text #10

Max Range: 0.2702. Min Range: -0.2702

Max Act: 0.2350. Min Act: -0.0001

Data Index: 94303 (C4 (Web Text))

Max Activating Token Index: 705

Text #11

Max Range: 0.2702. Min Range: -0.2702

Max Act: 0.2447. Min Act: -0.0001

Data Index: 961565 (C4 (Web Text))

Max Activating Token Index: 387

Text #12

Max Range: 0.2702. Min Range: -0.2702

Max Act: 0.2436. Min Act: -0.0001

Data Index: 292656 (C4 (Web Text))

Max Activating Token Index: 572

Text #13

Max Range: 0.2702. Min Range: -0.2702

Max Act: 0.2499. Min Act: -0.0001

Data Index: 1609787 (Python Code)

Max Activating Token Index: 446

Text #14

Max Range: 0.2702. Min Range: -0.2702

Max Act: 0.2331. Min Act: -0.0001

Data Index: 410402 (C4 (Web Text))

Max Activating Token Index: 648

Text #15

Max Range: 0.2702. Min Range: -0.2702

Max Act: 0.2403. Min Act: -0.0001

Data Index: 775327 (C4 (Web Text))

Max Activating Token Index: 41

Text #16

Max Range: 0.2702. Min Range: -0.2702

Max Act: 0.2411. Min Act: -0.0001

Data Index: 172221 (C4 (Web Text))

Max Activating Token Index: 662

Text #17

Max Range: 0.2702. Min Range: -0.2702

Max Act: 0.2199. Min Act: -0.0001

Data Index: 388991 (C4 (Web Text))

Max Activating Token Index: 959

Text #18

Max Range: 0.2702. Min Range: -0.2702

Max Act: 0.2335. Min Act: -0.0001

Data Index: 951522 (C4 (Web Text))

Max Activating Token Index: 997

Text #19

Max Range: 0.2702. Min Range: -0.2702

Max Act: 0.2250. Min Act: -0.0001

Data Index: 1324582 (C4 (Web Text))

Max Activating Token Index: 209