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

Dataset: The Pile

Neuron 3880 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5640. Min Range: -0.5640

Max Act: 0.5403. Min Act: -0.0000

Data Index: 1286942 (The Pile)

Max Activating Token Index: 1004

Text #1

Max Range: 0.5640. Min Range: -0.5640

Max Act: 0.5640. Min Act: -0.0000

Data Index: 845773 (The Pile)

Max Activating Token Index: 947

Text #2

Max Range: 0.5640. Min Range: -0.5640

Max Act: 0.5133. Min Act: -0.0000

Data Index: 454567 (The Pile)

Max Activating Token Index: 719

Text #3

Max Range: 0.5640. Min Range: -0.5640

Max Act: 0.5339. Min Act: -0.0000

Data Index: 444587 (The Pile)

Max Activating Token Index: 255

Text #4

Max Range: 0.5640. Min Range: -0.5640

Max Act: 0.4988. Min Act: -0.0000

Data Index: 1413424 (The Pile)

Max Activating Token Index: 275

Text #5

Max Range: 0.5640. Min Range: -0.5640

Max Act: 0.4640. Min Act: -0.0000

Data Index: 1349729 (The Pile)

Max Activating Token Index: 297

Text #6

Max Range: 0.5640. Min Range: -0.5640

Max Act: 0.4539. Min Act: -0.0000

Data Index: 1961807 (The Pile)

Max Activating Token Index: 190

Text #7

Max Range: 0.5640. Min Range: -0.5640

Max Act: 0.4613. Min Act: -0.0000

Data Index: 474873 (The Pile)

Max Activating Token Index: 25

Text #8

Max Range: 0.5640. Min Range: -0.5640

Max Act: 0.4629. Min Act: -0.0000

Data Index: 1949710 (The Pile)

Max Activating Token Index: 101

Text #9

Max Range: 0.5640. Min Range: -0.5640

Max Act: 0.4657. Min Act: -0.0000

Data Index: 1942536 (The Pile)

Max Activating Token Index: 473

Text #10

Max Range: 0.5640. Min Range: -0.5640

Max Act: 0.4406. Min Act: -0.0000

Data Index: 1955407 (The Pile)

Max Activating Token Index: 358

Text #11

Max Range: 0.5640. Min Range: -0.5640

Max Act: 0.4415. Min Act: -0.0000

Data Index: 878443 (The Pile)

Max Activating Token Index: 996

Text #12

Max Range: 0.5640. Min Range: -0.5640

Max Act: 0.4666. Min Act: -0.0000

Data Index: 304692 (The Pile)

Max Activating Token Index: 455

Text #13

Max Range: 0.5640. Min Range: -0.5640

Max Act: 0.4600. Min Act: -0.0000

Data Index: 190900 (The Pile)

Max Activating Token Index: 655

Text #14

Max Range: 0.5640. Min Range: -0.5640

Max Act: 0.4151. Min Act: -0.0000

Data Index: 1707130 (The Pile)

Max Activating Token Index: 87

Text #15

Max Range: 0.5640. Min Range: -0.5640

Max Act: 0.4543. Min Act: -0.0000

Data Index: 1837699 (The Pile)

Max Activating Token Index: 58

Text #16

Max Range: 0.5640. Min Range: -0.5640

Max Act: 0.5164. Min Act: -0.0000

Data Index: 751532 (The Pile)

Max Activating Token Index: 911

Text #17

Max Range: 0.5640. Min Range: -0.5640

Max Act: 0.4278. Min Act: -0.0000

Data Index: 1582680 (The Pile)

Max Activating Token Index: 278

Text #18

Max Range: 0.5640. Min Range: -0.5640

Max Act: 0.4288. Min Act: -0.0000

Data Index: 1789018 (The Pile)

Max Activating Token Index: 180

Text #19

Max Range: 0.5640. Min Range: -0.5640

Max Act: 0.4649. Min Act: -0.0000

Data Index: 1549213 (The Pile)

Max Activating Token Index: 635