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

Dataset: The Pile

Neuron 340 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8345. Min Range: -0.8345

Max Act: 0.8345. Min Act: -0.0000

Data Index: 898585 (The Pile)

Max Activating Token Index: 143

Text #1

Max Range: 0.8345. Min Range: -0.8345

Max Act: 0.7275. Min Act: -0.0000

Data Index: 324651 (The Pile)

Max Activating Token Index: 56

Text #2

Max Range: 0.8345. Min Range: -0.8345

Max Act: 0.7965. Min Act: -0.0000

Data Index: 220591 (The Pile)

Max Activating Token Index: 376

Text #3

Max Range: 0.8345. Min Range: -0.8345

Max Act: 0.7809. Min Act: -0.0000

Data Index: 70788 (The Pile)

Max Activating Token Index: 30

Text #4

Max Range: 0.8345. Min Range: -0.8345

Max Act: 0.7250. Min Act: -0.0000

Data Index: 605612 (The Pile)

Max Activating Token Index: 801

Text #5

Max Range: 0.8345. Min Range: -0.8345

Max Act: 0.7228. Min Act: -0.0000

Data Index: 183384 (The Pile)

Max Activating Token Index: 664

Text #6

Max Range: 0.8345. Min Range: -0.8345

Max Act: 0.7427. Min Act: -0.0000

Data Index: 1407144 (The Pile)

Max Activating Token Index: 241

Text #7

Max Range: 0.8345. Min Range: -0.8345

Max Act: 0.7499. Min Act: -0.0000

Data Index: 1172899 (The Pile)

Max Activating Token Index: 664

Text #8

Max Range: 0.8345. Min Range: -0.8345

Max Act: 0.7283. Min Act: -0.0000

Data Index: 1279273 (The Pile)

Max Activating Token Index: 42

Text #9

Max Range: 0.8345. Min Range: -0.8345

Max Act: 0.6670. Min Act: -0.0000

Data Index: 1866431 (The Pile)

Max Activating Token Index: 27

Text #10

Max Range: 0.8345. Min Range: -0.8345

Max Act: 0.7002. Min Act: -0.0000

Data Index: 1048980 (The Pile)

Max Activating Token Index: 296

Text #11

Max Range: 0.8345. Min Range: -0.8345

Max Act: 0.6717. Min Act: -0.0000

Data Index: 1723274 (The Pile)

Max Activating Token Index: 718

Text #12

Max Range: 0.8345. Min Range: -0.8345

Max Act: 0.7028. Min Act: -0.0000

Data Index: 1039002 (The Pile)

Max Activating Token Index: 775

Text #13

Max Range: 0.8345. Min Range: -0.8345

Max Act: 0.6620. Min Act: -0.0000

Data Index: 1263323 (The Pile)

Max Activating Token Index: 628

Text #14

Max Range: 0.8345. Min Range: -0.8345

Max Act: 0.6772. Min Act: -0.0000

Data Index: 1511400 (The Pile)

Max Activating Token Index: 485

Text #15

Max Range: 0.8345. Min Range: -0.8345

Max Act: 0.6891. Min Act: -0.0000

Data Index: 803618 (The Pile)

Max Activating Token Index: 68

Text #16

Max Range: 0.8345. Min Range: -0.8345

Max Act: 0.7105. Min Act: -0.0000

Data Index: 1487355 (The Pile)

Max Activating Token Index: 641

Text #17

Max Range: 0.8345. Min Range: -0.8345

Max Act: 0.6449. Min Act: -0.0000

Data Index: 427312 (The Pile)

Max Activating Token Index: 694

Text #18

Max Range: 0.8345. Min Range: -0.8345

Max Act: 0.6859. Min Act: -0.0000

Data Index: 1525206 (The Pile)

Max Activating Token Index: 529

Text #19

Max Range: 0.8345. Min Range: -0.8345

Max Act: 0.6588. Min Act: -0.0000

Data Index: 1324965 (The Pile)

Max Activating Token Index: 311