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

Dataset: The Pile

Neuron 612 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.2267. Min Range: -5.2267

Max Act: 5.2267. Min Act: -0.0000

Data Index: 270443 (The Pile)

Max Activating Token Index: 355

Text #1

Max Range: 5.2267. Min Range: -5.2267

Max Act: 4.3235. Min Act: -0.0000

Data Index: 191251 (The Pile)

Max Activating Token Index: 541

Text #2

Max Range: 5.2267. Min Range: -5.2267

Max Act: 3.9964. Min Act: -0.0000

Data Index: 227384 (The Pile)

Max Activating Token Index: 337

Text #3

Max Range: 5.2267. Min Range: -5.2267

Max Act: 3.3338. Min Act: 0.0000

Data Index: 705093 (The Pile)

Max Activating Token Index: 826

Text #4

Max Range: 5.2267. Min Range: -5.2267

Max Act: 3.9055. Min Act: 0.0000

Data Index: 1741670 (The Pile)

Max Activating Token Index: 746

Text #5

Max Range: 5.2267. Min Range: -5.2267

Max Act: 4.6921. Min Act: -0.0000

Data Index: 957514 (The Pile)

Max Activating Token Index: 612

Text #6

Max Range: 5.2267. Min Range: -5.2267

Max Act: 4.1051. Min Act: -0.0000

Data Index: 1068285 (The Pile)

Max Activating Token Index: 809

Text #7

Max Range: 5.2267. Min Range: -5.2267

Max Act: 3.8692. Min Act: -0.0000

Data Index: 1130588 (The Pile)

Max Activating Token Index: 575

Text #8

Max Range: 5.2267. Min Range: -5.2267

Max Act: 3.7172. Min Act: -0.0000

Data Index: 93229 (The Pile)

Max Activating Token Index: 973

Text #9

Max Range: 5.2267. Min Range: -5.2267

Max Act: 3.5154. Min Act: 0.0000

Data Index: 1534304 (The Pile)

Max Activating Token Index: 555

Text #10

Max Range: 5.2267. Min Range: -5.2267

Max Act: 3.7995. Min Act: -0.0000

Data Index: 1103956 (The Pile)

Max Activating Token Index: 814

Text #11

Max Range: 5.2267. Min Range: -5.2267

Max Act: 3.7587. Min Act: -0.0000

Data Index: 602612 (The Pile)

Max Activating Token Index: 971

Text #12

Max Range: 5.2267. Min Range: -5.2267

Max Act: 3.1608. Min Act: -0.0000

Data Index: 1482167 (The Pile)

Max Activating Token Index: 555

Text #13

Max Range: 5.2267. Min Range: -5.2267

Max Act: 2.7881. Min Act: -0.0000

Data Index: 1946944 (The Pile)

Max Activating Token Index: 695

Text #14

Max Range: 5.2267. Min Range: -5.2267

Max Act: 3.2359. Min Act: -0.0000

Data Index: 408353 (The Pile)

Max Activating Token Index: 884

Text #15

Max Range: 5.2267. Min Range: -5.2267

Max Act: 3.3485. Min Act: -0.0000

Data Index: 858467 (The Pile)

Max Activating Token Index: 169

Text #16

Max Range: 5.2267. Min Range: -5.2267

Max Act: 3.0561. Min Act: -0.0000

Data Index: 1760045 (The Pile)

Max Activating Token Index: 879

Text #17

Max Range: 5.2267. Min Range: -5.2267

Max Act: 3.0665. Min Act: -0.0000

Data Index: 1491932 (The Pile)

Max Activating Token Index: 737

Text #18

Max Range: 5.2267. Min Range: -5.2267

Max Act: 2.9815. Min Act: -0.0000

Data Index: 766549 (The Pile)

Max Activating Token Index: 929

Text #19

Max Range: 5.2267. Min Range: -5.2267

Max Act: 2.8638. Min Act: 0.0001

Data Index: 429177 (The Pile)

Max Activating Token Index: 839