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

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

Neuron 3598 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: 0.0826. Min Range: -0.0826

Max Act: 0.0826. Min Act: -0.0000

Data Index: 1562566 (Python Code)

Max Activating Token Index: 285

Text #1

Max Range: 0.0826. Min Range: -0.0826

Max Act: 0.0666. Min Act: -0.0000

Data Index: 1639209 (Python Code)

Max Activating Token Index: 260

Text #2

Max Range: 0.0826. Min Range: -0.0826

Max Act: 0.0494. Min Act: -0.0000

Data Index: 146434 (C4 (Web Text))

Max Activating Token Index: 137

Text #3

Max Range: 0.0826. Min Range: -0.0826

Max Act: 0.0509. Min Act: -0.0000

Data Index: 1537211 (Python Code)

Max Activating Token Index: 697

Text #4

Max Range: 0.0826. Min Range: -0.0826

Max Act: 0.0469. Min Act: -0.0000

Data Index: 117366 (C4 (Web Text))

Max Activating Token Index: 375

Text #5

Max Range: 0.0826. Min Range: -0.0826

Max Act: 0.0532. Min Act: -0.0000

Data Index: 347460 (C4 (Web Text))

Max Activating Token Index: 989

Text #6

Max Range: 0.0826. Min Range: -0.0826

Max Act: 0.0486. Min Act: -0.0000

Data Index: 773716 (C4 (Web Text))

Max Activating Token Index: 288

Text #7

Max Range: 0.0826. Min Range: -0.0826

Max Act: 0.0437. Min Act: -0.0000

Data Index: 387691 (C4 (Web Text))

Max Activating Token Index: 187

Text #8

Max Range: 0.0826. Min Range: -0.0826

Max Act: 0.0501. Min Act: -0.0000

Data Index: 457039 (C4 (Web Text))

Max Activating Token Index: 614

Text #9

Max Range: 0.0826. Min Range: -0.0826

Max Act: 0.0449. Min Act: -0.0000

Data Index: 512061 (C4 (Web Text))

Max Activating Token Index: 865

Text #10

Max Range: 0.0826. Min Range: -0.0826

Max Act: 0.0379. Min Act: -0.0000

Data Index: 99669 (C4 (Web Text))

Max Activating Token Index: 1000

Text #11

Max Range: 0.0826. Min Range: -0.0826

Max Act: 0.0437. Min Act: -0.0001

Data Index: 1397808 (Python Code)

Max Activating Token Index: 416

Text #12

Max Range: 0.0826. Min Range: -0.0826

Max Act: 0.0387. Min Act: -0.0000

Data Index: 722737 (C4 (Web Text))

Max Activating Token Index: 281

Text #13

Max Range: 0.0826. Min Range: -0.0826

Max Act: 0.0413. Min Act: -0.0000

Data Index: 992956 (C4 (Web Text))

Max Activating Token Index: 30

Text #14

Max Range: 0.0826. Min Range: -0.0826

Max Act: 0.0394. Min Act: -0.0000

Data Index: 549549 (C4 (Web Text))

Max Activating Token Index: 245

Text #15

Max Range: 0.0826. Min Range: -0.0826

Max Act: 0.0437. Min Act: -0.0000

Data Index: 256731 (C4 (Web Text))

Max Activating Token Index: 49

Text #16

Max Range: 0.0826. Min Range: -0.0826

Max Act: 0.0389. Min Act: -0.0000

Data Index: 881279 (C4 (Web Text))

Max Activating Token Index: 35

Text #17

Max Range: 0.0826. Min Range: -0.0826

Max Act: 0.0351. Min Act: -0.0000

Data Index: 1381165 (Python Code)

Max Activating Token Index: 481

Text #18

Max Range: 0.0826. Min Range: -0.0826

Max Act: 0.0372. Min Act: -0.0000

Data Index: 274104 (C4 (Web Text))

Max Activating Token Index: 87

Text #19

Max Range: 0.0826. Min Range: -0.0826

Max Act: 0.0431. Min Act: -0.0000

Data Index: 1518062 (Python Code)

Max Activating Token Index: 129