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

Dataset: The Pile

Neuron 1451 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2993. Min Range: -3.2993

Max Act: 3.2486. Min Act: -0.0000

Data Index: 1077681 (The Pile)

Max Activating Token Index: 92

Text #1

Max Range: 3.2993. Min Range: -3.2993

Max Act: 3.2001. Min Act: -0.0000

Data Index: 977143 (The Pile)

Max Activating Token Index: 412

Text #2

Max Range: 3.2993. Min Range: -3.2993

Max Act: 3.0474. Min Act: -0.0000

Data Index: 21525 (The Pile)

Max Activating Token Index: 788

Text #3

Max Range: 3.2993. Min Range: -3.2993

Max Act: 3.1079. Min Act: -0.0000

Data Index: 1879710 (The Pile)

Max Activating Token Index: 736

Text #4

Max Range: 3.2993. Min Range: -3.2993

Max Act: 2.9706. Min Act: -0.0000

Data Index: 1533884 (The Pile)

Max Activating Token Index: 494

Text #5

Max Range: 3.2993. Min Range: -3.2993

Max Act: 2.8980. Min Act: -0.0000

Data Index: 249635 (The Pile)

Max Activating Token Index: 948

Text #6

Max Range: 3.2993. Min Range: -3.2993

Max Act: 3.0806. Min Act: -0.0000

Data Index: 473011 (The Pile)

Max Activating Token Index: 655

Text #7

Max Range: 3.2993. Min Range: -3.2993

Max Act: 3.2993. Min Act: -0.0000

Data Index: 727256 (The Pile)

Max Activating Token Index: 658

Text #8

Max Range: 3.2993. Min Range: -3.2993

Max Act: 3.1473. Min Act: -0.0000

Data Index: 477873 (The Pile)

Max Activating Token Index: 626

Text #9

Max Range: 3.2993. Min Range: -3.2993

Max Act: 2.8662. Min Act: -0.0000

Data Index: 1096555 (The Pile)

Max Activating Token Index: 398

Text #10

Max Range: 3.2993. Min Range: -3.2993

Max Act: 2.8717. Min Act: -0.0000

Data Index: 1587755 (The Pile)

Max Activating Token Index: 813

Text #11

Max Range: 3.2993. Min Range: -3.2993

Max Act: 3.0213. Min Act: -0.0000

Data Index: 24405 (The Pile)

Max Activating Token Index: 707

Text #12

Max Range: 3.2993. Min Range: -3.2993

Max Act: 2.9829. Min Act: -0.0000

Data Index: 996201 (The Pile)

Max Activating Token Index: 147

Text #13

Max Range: 3.2993. Min Range: -3.2993

Max Act: 2.8376. Min Act: -0.0000

Data Index: 529287 (The Pile)

Max Activating Token Index: 443

Text #14

Max Range: 3.2993. Min Range: -3.2993

Max Act: 2.9581. Min Act: -0.0000

Data Index: 1524454 (The Pile)

Max Activating Token Index: 271

Text #15

Max Range: 3.2993. Min Range: -3.2993

Max Act: 3.1164. Min Act: -0.0000

Data Index: 476328 (The Pile)

Max Activating Token Index: 632

Text #16

Max Range: 3.2993. Min Range: -3.2993

Max Act: 2.8495. Min Act: -0.0000

Data Index: 721050 (The Pile)

Max Activating Token Index: 500

Text #17

Max Range: 3.2993. Min Range: -3.2993

Max Act: 2.6028. Min Act: -0.0000

Data Index: 1382455 (The Pile)

Max Activating Token Index: 784

Text #18

Max Range: 3.2993. Min Range: -3.2993

Max Act: 2.8382. Min Act: -0.0000

Data Index: 1117346 (The Pile)

Max Activating Token Index: 198

Text #19

Max Range: 3.2993. Min Range: -3.2993

Max Act: 3.1144. Min Act: -0.0000

Data Index: 615390 (The Pile)

Max Activating Token Index: 391