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

Dataset: The Pile

Neuron 1195 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: 5.1686. Min Range: -5.1686

Max Act: 5.1686. Min Act: -0.0000

Data Index: 1828481 (The Pile)

Max Activating Token Index: 742

Text #1

Max Range: 5.1686. Min Range: -5.1686

Max Act: 4.7967. Min Act: -0.0000

Data Index: 1384827 (The Pile)

Max Activating Token Index: 462

Text #2

Max Range: 5.1686. Min Range: -5.1686

Max Act: 4.7480. Min Act: -0.0000

Data Index: 165384 (The Pile)

Max Activating Token Index: 775

Text #3

Max Range: 5.1686. Min Range: -5.1686

Max Act: 4.7331. Min Act: -0.0000

Data Index: 1265773 (The Pile)

Max Activating Token Index: 559

Text #4

Max Range: 5.1686. Min Range: -5.1686

Max Act: 4.2170. Min Act: -0.0000

Data Index: 1282310 (The Pile)

Max Activating Token Index: 43

Text #5

Max Range: 5.1686. Min Range: -5.1686

Max Act: 4.0170. Min Act: -0.0000

Data Index: 1973924 (The Pile)

Max Activating Token Index: 719

Text #6

Max Range: 5.1686. Min Range: -5.1686

Max Act: 3.7885. Min Act: -0.0000

Data Index: 380128 (The Pile)

Max Activating Token Index: 1008

Text #7

Max Range: 5.1686. Min Range: -5.1686

Max Act: 4.0561. Min Act: -0.0000

Data Index: 477886 (The Pile)

Max Activating Token Index: 220

Text #8

Max Range: 5.1686. Min Range: -5.1686

Max Act: 3.5859. Min Act: -0.0000

Data Index: 765569 (The Pile)

Max Activating Token Index: 669

Text #9

Max Range: 5.1686. Min Range: -5.1686

Max Act: 3.8674. Min Act: -0.0000

Data Index: 1122683 (The Pile)

Max Activating Token Index: 913

Text #10

Max Range: 5.1686. Min Range: -5.1686

Max Act: 3.5343. Min Act: -0.0000

Data Index: 759473 (The Pile)

Max Activating Token Index: 658

Text #11

Max Range: 5.1686. Min Range: -5.1686

Max Act: 4.0146. Min Act: -0.0000

Data Index: 135083 (The Pile)

Max Activating Token Index: 473

Text #12

Max Range: 5.1686. Min Range: -5.1686

Max Act: 3.8339. Min Act: -0.0000

Data Index: 1316546 (The Pile)

Max Activating Token Index: 693

Text #13

Max Range: 5.1686. Min Range: -5.1686

Max Act: 4.0184. Min Act: -0.0000

Data Index: 1897525 (The Pile)

Max Activating Token Index: 776

Text #14

Max Range: 5.1686. Min Range: -5.1686

Max Act: 3.9430. Min Act: -0.0000

Data Index: 997147 (The Pile)

Max Activating Token Index: 69

Text #15

Max Range: 5.1686. Min Range: -5.1686

Max Act: 3.7313. Min Act: -0.0000

Data Index: 53524 (The Pile)

Max Activating Token Index: 907

Text #16

Max Range: 5.1686. Min Range: -5.1686

Max Act: 4.1018. Min Act: -0.0000

Data Index: 747686 (The Pile)

Max Activating Token Index: 930

Text #17

Max Range: 5.1686. Min Range: -5.1686

Max Act: 4.1961. Min Act: -0.0000

Data Index: 1788394 (The Pile)

Max Activating Token Index: 738

Text #18

Max Range: 5.1686. Min Range: -5.1686

Max Act: 3.9186. Min Act: -0.0000

Data Index: 709962 (The Pile)

Max Activating Token Index: 574

Text #19

Max Range: 5.1686. Min Range: -5.1686

Max Act: 3.7967. Min Act: -0.0000

Data Index: 1463271 (The Pile)

Max Activating Token Index: 869