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

Dataset: The Pile

Neuron 3668 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: 0.0657. Min Range: -0.0657

Max Act: 0.0657. Min Act: -0.0000

Data Index: 399350 (The Pile)

Max Activating Token Index: 304

Text #1

Max Range: 0.0657. Min Range: -0.0657

Max Act: 0.0543. Min Act: -0.0000

Data Index: 1122285 (The Pile)

Max Activating Token Index: 52

Text #2

Max Range: 0.0657. Min Range: -0.0657

Max Act: 0.0539. Min Act: -0.0000

Data Index: 1735070 (The Pile)

Max Activating Token Index: 465

Text #3

Max Range: 0.0657. Min Range: -0.0657

Max Act: 0.0512. Min Act: -0.0000

Data Index: 655937 (The Pile)

Max Activating Token Index: 180

Text #4

Max Range: 0.0657. Min Range: -0.0657

Max Act: 0.0549. Min Act: -0.0000

Data Index: 1337429 (The Pile)

Max Activating Token Index: 306

Text #5

Max Range: 0.0657. Min Range: -0.0657

Max Act: 0.0524. Min Act: -0.0000

Data Index: 1714103 (The Pile)

Max Activating Token Index: 431

Text #6

Max Range: 0.0657. Min Range: -0.0657

Max Act: 0.0542. Min Act: -0.0000

Data Index: 1610698 (The Pile)

Max Activating Token Index: 343

Text #7

Max Range: 0.0657. Min Range: -0.0657

Max Act: 0.0545. Min Act: -0.0000

Data Index: 1818788 (The Pile)

Max Activating Token Index: 598

Text #8

Max Range: 0.0657. Min Range: -0.0657

Max Act: 0.0493. Min Act: -0.0000

Data Index: 541767 (The Pile)

Max Activating Token Index: 17

Text #9

Max Range: 0.0657. Min Range: -0.0657

Max Act: 0.0504. Min Act: -0.0000

Data Index: 1800945 (The Pile)

Max Activating Token Index: 264

Text #10

Max Range: 0.0657. Min Range: -0.0657

Max Act: 0.0538. Min Act: -0.0000

Data Index: 1031063 (The Pile)

Max Activating Token Index: 48

Text #11

Max Range: 0.0657. Min Range: -0.0657

Max Act: 0.0500. Min Act: -0.0000

Data Index: 776960 (The Pile)

Max Activating Token Index: 208

Text #12

Max Range: 0.0657. Min Range: -0.0657

Max Act: 0.0518. Min Act: -0.0000

Data Index: 1531599 (The Pile)

Max Activating Token Index: 260

Text #13

Max Range: 0.0657. Min Range: -0.0657

Max Act: 0.0518. Min Act: -0.0000

Data Index: 504626 (The Pile)

Max Activating Token Index: 935

Text #14

Max Range: 0.0657. Min Range: -0.0657

Max Act: 0.0480. Min Act: -0.0000

Data Index: 1260070 (The Pile)

Max Activating Token Index: 519

Text #15

Max Range: 0.0657. Min Range: -0.0657

Max Act: 0.0503. Min Act: -0.0000

Data Index: 1005078 (The Pile)

Max Activating Token Index: 584

Text #16

Max Range: 0.0657. Min Range: -0.0657

Max Act: 0.0515. Min Act: -0.0000

Data Index: 983856 (The Pile)

Max Activating Token Index: 329

Text #17

Max Range: 0.0657. Min Range: -0.0657

Max Act: 0.0515. Min Act: -0.0000

Data Index: 907562 (The Pile)

Max Activating Token Index: 129

Text #18

Max Range: 0.0657. Min Range: -0.0657

Max Act: 0.0517. Min Act: -0.0000

Data Index: 1916188 (The Pile)

Max Activating Token Index: 510

Text #19

Max Range: 0.0657. Min Range: -0.0657

Max Act: 0.0498. Min Act: -0.0000

Data Index: 884640 (The Pile)

Max Activating Token Index: 583