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

Dataset: The Pile

Neuron 1943 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: 1.5578. Min Range: -1.5578

Max Act: 1.5367. Min Act: -0.0000

Data Index: 1259181 (The Pile)

Max Activating Token Index: 860

Text #1

Max Range: 1.5578. Min Range: -1.5578

Max Act: 1.5578. Min Act: -0.0000

Data Index: 1004227 (The Pile)

Max Activating Token Index: 787

Text #2

Max Range: 1.5578. Min Range: -1.5578

Max Act: 1.3562. Min Act: -0.0000

Data Index: 1244408 (The Pile)

Max Activating Token Index: 622

Text #3

Max Range: 1.5578. Min Range: -1.5578

Max Act: 1.3077. Min Act: -0.0000

Data Index: 277080 (The Pile)

Max Activating Token Index: 610

Text #4

Max Range: 1.5578. Min Range: -1.5578

Max Act: 1.3819. Min Act: -0.0000

Data Index: 443455 (The Pile)

Max Activating Token Index: 839

Text #5

Max Range: 1.5578. Min Range: -1.5578

Max Act: 1.4074. Min Act: -0.0000

Data Index: 997312 (The Pile)

Max Activating Token Index: 789

Text #6

Max Range: 1.5578. Min Range: -1.5578

Max Act: 1.3356. Min Act: -0.0000

Data Index: 93247 (The Pile)

Max Activating Token Index: 908

Text #7

Max Range: 1.5578. Min Range: -1.5578

Max Act: 1.2640. Min Act: -0.0000

Data Index: 610242 (The Pile)

Max Activating Token Index: 484

Text #8

Max Range: 1.5578. Min Range: -1.5578

Max Act: 1.3234. Min Act: -0.0000

Data Index: 1076427 (The Pile)

Max Activating Token Index: 807

Text #9

Max Range: 1.5578. Min Range: -1.5578

Max Act: 1.4226. Min Act: -0.0000

Data Index: 772140 (The Pile)

Max Activating Token Index: 930

Text #10

Max Range: 1.5578. Min Range: -1.5578

Max Act: 1.4068. Min Act: -0.0000

Data Index: 1455722 (The Pile)

Max Activating Token Index: 808

Text #11

Max Range: 1.5578. Min Range: -1.5578

Max Act: 1.3545. Min Act: -0.0000

Data Index: 1171744 (The Pile)

Max Activating Token Index: 756

Text #12

Max Range: 1.5578. Min Range: -1.5578

Max Act: 1.3579. Min Act: -0.0000

Data Index: 955909 (The Pile)

Max Activating Token Index: 500

Text #13

Max Range: 1.5578. Min Range: -1.5578

Max Act: 1.3582. Min Act: -0.0000

Data Index: 1331704 (The Pile)

Max Activating Token Index: 522

Text #14

Max Range: 1.5578. Min Range: -1.5578

Max Act: 1.3093. Min Act: -0.0000

Data Index: 1172473 (The Pile)

Max Activating Token Index: 473

Text #15

Max Range: 1.5578. Min Range: -1.5578

Max Act: 1.3519. Min Act: -0.0000

Data Index: 1926071 (The Pile)

Max Activating Token Index: 525

Text #16

Max Range: 1.5578. Min Range: -1.5578

Max Act: 1.3416. Min Act: -0.0000

Data Index: 1450590 (The Pile)

Max Activating Token Index: 631

Text #17

Max Range: 1.5578. Min Range: -1.5578

Max Act: 1.2979. Min Act: -0.0000

Data Index: 371616 (The Pile)

Max Activating Token Index: 624

Text #18

Max Range: 1.5578. Min Range: -1.5578

Max Act: 1.2637. Min Act: -0.0000

Data Index: 717401 (The Pile)

Max Activating Token Index: 743

Text #19

Max Range: 1.5578. Min Range: -1.5578

Max Act: 1.3285. Min Act: -0.0000

Data Index: 514646 (The Pile)

Max Activating Token Index: 723