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

Dataset: The Pile

Neuron 3123 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0540. Min Range: -1.0540

Max Act: 0.9631. Min Act: -0.0000

Data Index: 1960515 (The Pile)

Max Activating Token Index: 778

Text #1

Max Range: 1.0540. Min Range: -1.0540

Max Act: 1.0163. Min Act: -0.0000

Data Index: 346260 (The Pile)

Max Activating Token Index: 647

Text #2

Max Range: 1.0540. Min Range: -1.0540

Max Act: 0.9910. Min Act: 0.0000

Data Index: 1797700 (The Pile)

Max Activating Token Index: 34

Text #3

Max Range: 1.0540. Min Range: -1.0540

Max Act: 1.0540. Min Act: -0.0000

Data Index: 653264 (The Pile)

Max Activating Token Index: 428

Text #4

Max Range: 1.0540. Min Range: -1.0540

Max Act: 1.0494. Min Act: -0.0000

Data Index: 1624273 (The Pile)

Max Activating Token Index: 54

Text #5

Max Range: 1.0540. Min Range: -1.0540

Max Act: 1.0166. Min Act: -0.0000

Data Index: 1702913 (The Pile)

Max Activating Token Index: 825

Text #6

Max Range: 1.0540. Min Range: -1.0540

Max Act: 1.0145. Min Act: -0.0000

Data Index: 1285727 (The Pile)

Max Activating Token Index: 38

Text #7

Max Range: 1.0540. Min Range: -1.0540

Max Act: 0.9681. Min Act: -0.0000

Data Index: 467925 (The Pile)

Max Activating Token Index: 38

Text #8

Max Range: 1.0540. Min Range: -1.0540

Max Act: 0.9962. Min Act: -0.0000

Data Index: 48804 (The Pile)

Max Activating Token Index: 744

Text #9

Max Range: 1.0540. Min Range: -1.0540

Max Act: 1.0492. Min Act: -0.0000

Data Index: 54582 (The Pile)

Max Activating Token Index: 712

Text #10

Max Range: 1.0540. Min Range: -1.0540

Max Act: 0.9658. Min Act: -0.0000

Data Index: 1037513 (The Pile)

Max Activating Token Index: 139

Text #11

Max Range: 1.0540. Min Range: -1.0540

Max Act: 0.8036. Min Act: -0.0000

Data Index: 1245200 (The Pile)

Max Activating Token Index: 443

Text #12

Max Range: 1.0540. Min Range: -1.0540

Max Act: 0.9864. Min Act: -0.0000

Data Index: 1057318 (The Pile)

Max Activating Token Index: 802

Text #13

Max Range: 1.0540. Min Range: -1.0540

Max Act: 0.8710. Min Act: -0.0000

Data Index: 1736205 (The Pile)

Max Activating Token Index: 27

Text #14

Max Range: 1.0540. Min Range: -1.0540

Max Act: 0.8103. Min Act: -0.0000

Data Index: 985236 (The Pile)

Max Activating Token Index: 445

Text #15

Max Range: 1.0540. Min Range: -1.0540

Max Act: 0.7950. Min Act: -0.0000

Data Index: 1548217 (The Pile)

Max Activating Token Index: 654

Text #16

Max Range: 1.0540. Min Range: -1.0540

Max Act: 0.8599. Min Act: -0.0000

Data Index: 458314 (The Pile)

Max Activating Token Index: 316

Text #17

Max Range: 1.0540. Min Range: -1.0540

Max Act: 0.8885. Min Act: -0.0000

Data Index: 1124731 (The Pile)

Max Activating Token Index: 335

Text #18

Max Range: 1.0540. Min Range: -1.0540

Max Act: 0.8114. Min Act: -0.0000

Data Index: 1920788 (The Pile)

Max Activating Token Index: 36

Text #19

Max Range: 1.0540. Min Range: -1.0540

Max Act: 0.8376. Min Act: -0.0000

Data Index: 1905780 (The Pile)

Max Activating Token Index: 464