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

Dataset: The Pile

Neuron 3578 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0578. Min Act: -0.0000

Data Index: 85850 (The Pile)

Max Activating Token Index: 88

Text #1

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0615. Min Act: 0.0000

Data Index: 1164949 (The Pile)

Max Activating Token Index: 1023

Text #2

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0573. Min Act: 0.0000

Data Index: 950644 (The Pile)

Max Activating Token Index: 734

Text #3

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0540. Min Act: -0.0000

Data Index: 523740 (The Pile)

Max Activating Token Index: 388

Text #4

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0534. Min Act: 0.0000

Data Index: 1412989 (The Pile)

Max Activating Token Index: 504

Text #5

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0528. Min Act: 0.0000

Data Index: 601344 (The Pile)

Max Activating Token Index: 24

Text #6

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0526. Min Act: 0.0000

Data Index: 939372 (The Pile)

Max Activating Token Index: 686

Text #7

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0516. Min Act: -0.0000

Data Index: 339567 (The Pile)

Max Activating Token Index: 35

Text #8

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0512. Min Act: 0.0000

Data Index: 371128 (The Pile)

Max Activating Token Index: 907

Text #9

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0508. Min Act: 0.0000

Data Index: 141880 (The Pile)

Max Activating Token Index: 225

Text #10

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0492. Min Act: 0.0000

Data Index: 255037 (The Pile)

Max Activating Token Index: 141

Text #11

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0505. Min Act: 0.0000

Data Index: 187159 (The Pile)

Max Activating Token Index: 614

Text #12

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0487. Min Act: 0.0000

Data Index: 998434 (The Pile)

Max Activating Token Index: 263

Text #13

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0482. Min Act: 0.0000

Data Index: 1189490 (The Pile)

Max Activating Token Index: 384

Text #14

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0481. Min Act: 0.0000

Data Index: 1221034 (The Pile)

Max Activating Token Index: 911

Text #15

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0480. Min Act: 0.0000

Data Index: 1938129 (The Pile)

Max Activating Token Index: 22

Text #16

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0498. Min Act: 0.0000

Data Index: 128399 (The Pile)

Max Activating Token Index: 30

Text #17

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0479. Min Act: 0.0000

Data Index: 273086 (The Pile)

Max Activating Token Index: 488

Text #18

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0476. Min Act: 0.0000

Data Index: 401609 (The Pile)

Max Activating Token Index: 63

Text #19

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0476. Min Act: 0.0000

Data Index: 1442875 (The Pile)

Max Activating Token Index: 12