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

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

Neuron 2785 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0628. Min Act: -0.0001

Data Index: 1487316 (Python Code)

Max Activating Token Index: 1008

Text #1

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0477. Min Act: -0.0001

Data Index: 1415959 (Python Code)

Max Activating Token Index: 737

Text #2

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0485. Min Act: -0.0001

Data Index: 1621749 (Python Code)

Max Activating Token Index: 802

Text #3

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0457. Min Act: -0.0000

Data Index: 1486325 (Python Code)

Max Activating Token Index: 592

Text #4

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0436. Min Act: -0.0001

Data Index: 851520 (C4 (Web Text))

Max Activating Token Index: 678

Text #5

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0418. Min Act: -0.0000

Data Index: 1393300 (Python Code)

Max Activating Token Index: 1013

Text #6

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0420. Min Act: -0.0000

Data Index: 1590573 (Python Code)

Max Activating Token Index: 637

Text #7

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0373. Min Act: -0.0001

Data Index: 1069752 (C4 (Web Text))

Max Activating Token Index: 812

Text #8

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0384. Min Act: -0.0000

Data Index: 1487948 (Python Code)

Max Activating Token Index: 573

Text #9

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0425. Min Act: -0.0001

Data Index: 1645307 (Python Code)

Max Activating Token Index: 963

Text #10

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0407. Min Act: -0.0001

Data Index: 864228 (C4 (Web Text))

Max Activating Token Index: 819

Text #11

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0385. Min Act: -0.0000

Data Index: 1413420 (Python Code)

Max Activating Token Index: 978

Text #12

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0333. Min Act: -0.0001

Data Index: 1375993 (Python Code)

Max Activating Token Index: 312

Text #13

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0371. Min Act: -0.0001

Data Index: 1483614 (Python Code)

Max Activating Token Index: 872

Text #14

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0374. Min Act: -0.0001

Data Index: 1422959 (Python Code)

Max Activating Token Index: 823

Text #15

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0364. Min Act: -0.0001

Data Index: 1450565 (Python Code)

Max Activating Token Index: 214

Text #16

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0351. Min Act: -0.0001

Data Index: 1590795 (Python Code)

Max Activating Token Index: 709

Text #17

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0310. Min Act: -0.0001

Data Index: 261627 (C4 (Web Text))

Max Activating Token Index: 904

Text #18

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0347. Min Act: -0.0001

Data Index: 1601477 (Python Code)

Max Activating Token Index: 931

Text #19

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0332. Min Act: -0.0001

Data Index: 1528580 (Python Code)

Max Activating Token Index: 744