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

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

Neuron 1578 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0928. Min Range: -0.0928

Max Act: 0.0928. Min Act: -0.0001

Data Index: 96312 (C4 (Web Text))

Max Activating Token Index: 199

Text #1

Max Range: 0.0928. Min Range: -0.0928

Max Act: 0.0775. Min Act: -0.0001

Data Index: 1605778 (Python Code)

Max Activating Token Index: 960

Text #2

Max Range: 0.0928. Min Range: -0.0928

Max Act: 0.0801. Min Act: -0.0001

Data Index: 1469440 (Python Code)

Max Activating Token Index: 398

Text #3

Max Range: 0.0928. Min Range: -0.0928

Max Act: 0.0747. Min Act: -0.0001

Data Index: 1448122 (Python Code)

Max Activating Token Index: 413

Text #4

Max Range: 0.0928. Min Range: -0.0928

Max Act: 0.0707. Min Act: -0.0001

Data Index: 1398052 (Python Code)

Max Activating Token Index: 123

Text #5

Max Range: 0.0928. Min Range: -0.0928

Max Act: 0.0646. Min Act: -0.0001

Data Index: 1567998 (Python Code)

Max Activating Token Index: 727

Text #6

Max Range: 0.0928. Min Range: -0.0928

Max Act: 0.0703. Min Act: -0.0001

Data Index: 1195641 (C4 (Web Text))

Max Activating Token Index: 649

Text #7

Max Range: 0.0928. Min Range: -0.0928

Max Act: 0.0596. Min Act: -0.0001

Data Index: 275558 (C4 (Web Text))

Max Activating Token Index: 468

Text #8

Max Range: 0.0928. Min Range: -0.0928

Max Act: 0.0634. Min Act: -0.0001

Data Index: 1587625 (Python Code)

Max Activating Token Index: 48

Text #9

Max Range: 0.0928. Min Range: -0.0928

Max Act: 0.0589. Min Act: -0.0001

Data Index: 1405230 (Python Code)

Max Activating Token Index: 375

Text #10

Max Range: 0.0928. Min Range: -0.0928

Max Act: 0.0607. Min Act: -0.0001

Data Index: 294239 (C4 (Web Text))

Max Activating Token Index: 123

Text #11

Max Range: 0.0928. Min Range: -0.0928

Max Act: 0.0543. Min Act: -0.0001

Data Index: 877903 (C4 (Web Text))

Max Activating Token Index: 773

Text #12

Max Range: 0.0928. Min Range: -0.0928

Max Act: 0.0612. Min Act: -0.0001

Data Index: 486300 (C4 (Web Text))

Max Activating Token Index: 632

Text #13

Max Range: 0.0928. Min Range: -0.0928

Max Act: 0.0581. Min Act: -0.0001

Data Index: 1646302 (Python Code)

Max Activating Token Index: 409

Text #14

Max Range: 0.0928. Min Range: -0.0928

Max Act: 0.0586. Min Act: -0.0001

Data Index: 1618387 (Python Code)

Max Activating Token Index: 457

Text #15

Max Range: 0.0928. Min Range: -0.0928

Max Act: 0.0583. Min Act: -0.0001

Data Index: 1589878 (Python Code)

Max Activating Token Index: 64

Text #16

Max Range: 0.0928. Min Range: -0.0928

Max Act: 0.0557. Min Act: -0.0001

Data Index: 1130800 (C4 (Web Text))

Max Activating Token Index: 134

Text #17

Max Range: 0.0928. Min Range: -0.0928

Max Act: 0.0556. Min Act: -0.0001

Data Index: 1267081 (C4 (Web Text))

Max Activating Token Index: 128

Text #18

Max Range: 0.0928. Min Range: -0.0928

Max Act: 0.0557. Min Act: -0.0001

Data Index: 1002560 (C4 (Web Text))

Max Activating Token Index: 520

Text #19

Max Range: 0.0928. Min Range: -0.0928

Max Act: 0.0533. Min Act: -0.0001

Data Index: 94093 (C4 (Web Text))

Max Activating Token Index: 428