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

Dataset: The Pile

Neuron 4009 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0473. Min Range: -1.0473

Max Act: 1.0473. Min Act: -0.0000

Data Index: 288377 (The Pile)

Max Activating Token Index: 804

Text #1

Max Range: 1.0473. Min Range: -1.0473

Max Act: 0.9521. Min Act: -0.0000

Data Index: 735375 (The Pile)

Max Activating Token Index: 736

Text #2

Max Range: 1.0473. Min Range: -1.0473

Max Act: 0.7336. Min Act: -0.0000

Data Index: 526747 (The Pile)

Max Activating Token Index: 30

Text #3

Max Range: 1.0473. Min Range: -1.0473

Max Act: 0.5397. Min Act: -0.0000

Data Index: 1213459 (The Pile)

Max Activating Token Index: 856

Text #4

Max Range: 1.0473. Min Range: -1.0473

Max Act: 0.7390. Min Act: -0.0000

Data Index: 422746 (The Pile)

Max Activating Token Index: 157

Text #5

Max Range: 1.0473. Min Range: -1.0473

Max Act: 0.6633. Min Act: -0.0000

Data Index: 42423 (The Pile)

Max Activating Token Index: 628

Text #6

Max Range: 1.0473. Min Range: -1.0473

Max Act: 0.6494. Min Act: -0.0000

Data Index: 656332 (The Pile)

Max Activating Token Index: 534

Text #7

Max Range: 1.0473. Min Range: -1.0473

Max Act: 0.6243. Min Act: -0.0000

Data Index: 1342067 (The Pile)

Max Activating Token Index: 1005

Text #8

Max Range: 1.0473. Min Range: -1.0473

Max Act: 0.5822. Min Act: -0.0000

Data Index: 650056 (The Pile)

Max Activating Token Index: 987

Text #9

Max Range: 1.0473. Min Range: -1.0473

Max Act: 0.6379. Min Act: -0.0000

Data Index: 1959430 (The Pile)

Max Activating Token Index: 210

Text #10

Max Range: 1.0473. Min Range: -1.0473

Max Act: 0.6058. Min Act: -0.0000

Data Index: 399799 (The Pile)

Max Activating Token Index: 418

Text #11

Max Range: 1.0473. Min Range: -1.0473

Max Act: 0.5601. Min Act: -0.0000

Data Index: 553290 (The Pile)

Max Activating Token Index: 572

Text #12

Max Range: 1.0473. Min Range: -1.0473

Max Act: 0.5802. Min Act: -0.0000

Data Index: 1429232 (The Pile)

Max Activating Token Index: 392

Text #13

Max Range: 1.0473. Min Range: -1.0473

Max Act: 0.5769. Min Act: -0.0000

Data Index: 1235389 (The Pile)

Max Activating Token Index: 782

Text #14

Max Range: 1.0473. Min Range: -1.0473

Max Act: 0.5354. Min Act: -0.0000

Data Index: 1081058 (The Pile)

Max Activating Token Index: 216

Text #15

Max Range: 1.0473. Min Range: -1.0473

Max Act: 0.6024. Min Act: -0.0000

Data Index: 1373033 (The Pile)

Max Activating Token Index: 477

Text #16

Max Range: 1.0473. Min Range: -1.0473

Max Act: 0.5294. Min Act: -0.0000

Data Index: 994604 (The Pile)

Max Activating Token Index: 38

Text #17

Max Range: 1.0473. Min Range: -1.0473

Max Act: 0.5555. Min Act: -0.0000

Data Index: 262499 (The Pile)

Max Activating Token Index: 588

Text #18

Max Range: 1.0473. Min Range: -1.0473

Max Act: 0.5738. Min Act: -0.0000

Data Index: 778076 (The Pile)

Max Activating Token Index: 662

Text #19

Max Range: 1.0473. Min Range: -1.0473

Max Act: 0.6082. Min Act: -0.0000

Data Index: 155162 (The Pile)

Max Activating Token Index: 264