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

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

Neuron 1579 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0547. Min Range: -0.0547

Max Act: 0.0547. Min Act: -0.0000

Data Index: 204952 (C4 (Web Text))

Max Activating Token Index: 333

Text #1

Max Range: 0.0547. Min Range: -0.0547

Max Act: 0.0473. Min Act: -0.0001

Data Index: 658829 (C4 (Web Text))

Max Activating Token Index: 91

Text #2

Max Range: 0.0547. Min Range: -0.0547

Max Act: 0.0464. Min Act: -0.0000

Data Index: 936856 (C4 (Web Text))

Max Activating Token Index: 968

Text #3

Max Range: 0.0547. Min Range: -0.0547

Max Act: 0.0457. Min Act: -0.0001

Data Index: 798211 (C4 (Web Text))

Max Activating Token Index: 673

Text #4

Max Range: 0.0547. Min Range: -0.0547

Max Act: 0.0419. Min Act: -0.0001

Data Index: 104064 (C4 (Web Text))

Max Activating Token Index: 1009

Text #5

Max Range: 0.0547. Min Range: -0.0547

Max Act: 0.0403. Min Act: -0.0001

Data Index: 1550077 (Python Code)

Max Activating Token Index: 386

Text #6

Max Range: 0.0547. Min Range: -0.0547

Max Act: 0.0397. Min Act: -0.0000

Data Index: 751966 (C4 (Web Text))

Max Activating Token Index: 847

Text #7

Max Range: 0.0547. Min Range: -0.0547

Max Act: 0.0385. Min Act: -0.0000

Data Index: 1212135 (C4 (Web Text))

Max Activating Token Index: 89

Text #8

Max Range: 0.0547. Min Range: -0.0547

Max Act: 0.0391. Min Act: -0.0000

Data Index: 734671 (C4 (Web Text))

Max Activating Token Index: 64

Text #9

Max Range: 0.0547. Min Range: -0.0547

Max Act: 0.0371. Min Act: -0.0001

Data Index: 399322 (C4 (Web Text))

Max Activating Token Index: 73

Text #10

Max Range: 0.0547. Min Range: -0.0547

Max Act: 0.0386. Min Act: -0.0001

Data Index: 1514933 (Python Code)

Max Activating Token Index: 437

Text #11

Max Range: 0.0547. Min Range: -0.0547

Max Act: 0.0382. Min Act: -0.0000

Data Index: 357944 (C4 (Web Text))

Max Activating Token Index: 1003

Text #12

Max Range: 0.0547. Min Range: -0.0547

Max Act: 0.0342. Min Act: -0.0001

Data Index: 1472985 (Python Code)

Max Activating Token Index: 617

Text #13

Max Range: 0.0547. Min Range: -0.0547

Max Act: 0.0346. Min Act: -0.0000

Data Index: 526290 (C4 (Web Text))

Max Activating Token Index: 563

Text #14

Max Range: 0.0547. Min Range: -0.0547

Max Act: 0.0339. Min Act: -0.0001

Data Index: 851679 (C4 (Web Text))

Max Activating Token Index: 328

Text #15

Max Range: 0.0547. Min Range: -0.0547

Max Act: 0.0374. Min Act: -0.0001

Data Index: 609443 (C4 (Web Text))

Max Activating Token Index: 69

Text #16

Max Range: 0.0547. Min Range: -0.0547

Max Act: 0.0325. Min Act: -0.0001

Data Index: 1561204 (Python Code)

Max Activating Token Index: 482

Text #17

Max Range: 0.0547. Min Range: -0.0547

Max Act: 0.0317. Min Act: -0.0000

Data Index: 301341 (C4 (Web Text))

Max Activating Token Index: 409

Text #18

Max Range: 0.0547. Min Range: -0.0547

Max Act: 0.0336. Min Act: -0.0001

Data Index: 1198007 (C4 (Web Text))

Max Activating Token Index: 451

Text #19

Max Range: 0.0547. Min Range: -0.0547

Max Act: 0.0331. Min Act: -0.0001

Data Index: 1414940 (Python Code)

Max Activating Token Index: 543