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

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

Neuron 273 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5655. Min Range: -0.5655

Max Act: 0.5655. Min Act: -0.0001

Data Index: 469671 (C4 (Web Text))

Max Activating Token Index: 434

Text #1

Max Range: 0.5655. Min Range: -0.5655

Max Act: 0.5160. Min Act: 0.0000

Data Index: 837873 (C4 (Web Text))

Max Activating Token Index: 222

Text #2

Max Range: 0.5655. Min Range: -0.5655

Max Act: 0.5060. Min Act: -0.0001

Data Index: 518415 (C4 (Web Text))

Max Activating Token Index: 828

Text #3

Max Range: 0.5655. Min Range: -0.5655

Max Act: 0.4634. Min Act: 0.0001

Data Index: 1002414 (C4 (Web Text))

Max Activating Token Index: 752

Text #4

Max Range: 0.5655. Min Range: -0.5655

Max Act: 0.4770. Min Act: -0.0000

Data Index: 1641957 (Python Code)

Max Activating Token Index: 414

Text #5

Max Range: 0.5655. Min Range: -0.5655

Max Act: 0.4691. Min Act: -0.0000

Data Index: 1419404 (Python Code)

Max Activating Token Index: 714

Text #6

Max Range: 0.5655. Min Range: -0.5655

Max Act: 0.4495. Min Act: -0.0000

Data Index: 1628235 (Python Code)

Max Activating Token Index: 457

Text #7

Max Range: 0.5655. Min Range: -0.5655

Max Act: 0.4732. Min Act: -0.0001

Data Index: 178436 (C4 (Web Text))

Max Activating Token Index: 799

Text #8

Max Range: 0.5655. Min Range: -0.5655

Max Act: 0.4123. Min Act: -0.0001

Data Index: 972218 (C4 (Web Text))

Max Activating Token Index: 790

Text #9

Max Range: 0.5655. Min Range: -0.5655

Max Act: 0.4797. Min Act: -0.0001

Data Index: 1173456 (C4 (Web Text))

Max Activating Token Index: 414

Text #10

Max Range: 0.5655. Min Range: -0.5655

Max Act: 0.3702. Min Act: -0.0001

Data Index: 122121 (C4 (Web Text))

Max Activating Token Index: 770

Text #11

Max Range: 0.5655. Min Range: -0.5655

Max Act: 0.4475. Min Act: -0.0000

Data Index: 713190 (C4 (Web Text))

Max Activating Token Index: 528

Text #12

Max Range: 0.5655. Min Range: -0.5655

Max Act: 0.3512. Min Act: -0.0000

Data Index: 434456 (C4 (Web Text))

Max Activating Token Index: 52

Text #13

Max Range: 0.5655. Min Range: -0.5655

Max Act: 0.4375. Min Act: -0.0000

Data Index: 1645399 (Python Code)

Max Activating Token Index: 417

Text #14

Max Range: 0.5655. Min Range: -0.5655

Max Act: 0.4377. Min Act: -0.0001

Data Index: 983628 (C4 (Web Text))

Max Activating Token Index: 543

Text #15

Max Range: 0.5655. Min Range: -0.5655

Max Act: 0.3835. Min Act: -0.0001

Data Index: 1514440 (Python Code)

Max Activating Token Index: 554

Text #16

Max Range: 0.5655. Min Range: -0.5655

Max Act: 0.3921. Min Act: 0.0001

Data Index: 1293490 (C4 (Web Text))

Max Activating Token Index: 416

Text #17

Max Range: 0.5655. Min Range: -0.5655

Max Act: 0.3859. Min Act: -0.0001

Data Index: 1190739 (C4 (Web Text))

Max Activating Token Index: 123

Text #18

Max Range: 0.5655. Min Range: -0.5655

Max Act: 0.3971. Min Act: -0.0000

Data Index: 1631734 (Python Code)

Max Activating Token Index: 952

Text #19

Max Range: 0.5655. Min Range: -0.5655

Max Act: 0.3957. Min Act: -0.0000

Data Index: 744209 (C4 (Web Text))

Max Activating Token Index: 264