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

Dataset: The Pile

Neuron 3024 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: 3.4340. Min Range: -3.4340

Max Act: 3.4340. Min Act: -0.0000

Data Index: 686327 (The Pile)

Max Activating Token Index: 592

Text #1

Max Range: 3.4340. Min Range: -3.4340

Max Act: 3.1576. Min Act: -0.0000

Data Index: 115367 (The Pile)

Max Activating Token Index: 765

Text #2

Max Range: 3.4340. Min Range: -3.4340

Max Act: 3.4239. Min Act: -0.0000

Data Index: 1887939 (The Pile)

Max Activating Token Index: 252

Text #3

Max Range: 3.4340. Min Range: -3.4340

Max Act: 3.1156. Min Act: -0.0000

Data Index: 248558 (The Pile)

Max Activating Token Index: 270

Text #4

Max Range: 3.4340. Min Range: -3.4340

Max Act: 3.2164. Min Act: -0.0000

Data Index: 82450 (The Pile)

Max Activating Token Index: 1006

Text #5

Max Range: 3.4340. Min Range: -3.4340

Max Act: 3.0633. Min Act: -0.0000

Data Index: 1085137 (The Pile)

Max Activating Token Index: 937

Text #6

Max Range: 3.4340. Min Range: -3.4340

Max Act: 3.0322. Min Act: 0.0000

Data Index: 1343382 (The Pile)

Max Activating Token Index: 703

Text #7

Max Range: 3.4340. Min Range: -3.4340

Max Act: 2.7170. Min Act: -0.0000

Data Index: 1645129 (The Pile)

Max Activating Token Index: 163

Text #8

Max Range: 3.4340. Min Range: -3.4340

Max Act: 3.0578. Min Act: -0.0000

Data Index: 870129 (The Pile)

Max Activating Token Index: 1002

Text #9

Max Range: 3.4340. Min Range: -3.4340

Max Act: 3.0508. Min Act: -0.0000

Data Index: 1555315 (The Pile)

Max Activating Token Index: 430

Text #10

Max Range: 3.4340. Min Range: -3.4340

Max Act: 3.0339. Min Act: -0.0000

Data Index: 1073460 (The Pile)

Max Activating Token Index: 571

Text #11

Max Range: 3.4340. Min Range: -3.4340

Max Act: 2.9801. Min Act: 0.0000

Data Index: 572393 (The Pile)

Max Activating Token Index: 443

Text #12

Max Range: 3.4340. Min Range: -3.4340

Max Act: 2.9828. Min Act: -0.0000

Data Index: 1164598 (The Pile)

Max Activating Token Index: 507

Text #13

Max Range: 3.4340. Min Range: -3.4340

Max Act: 3.1278. Min Act: -0.0000

Data Index: 902389 (The Pile)

Max Activating Token Index: 182

Text #14

Max Range: 3.4340. Min Range: -3.4340

Max Act: 2.9968. Min Act: -0.0000

Data Index: 499892 (The Pile)

Max Activating Token Index: 895

Text #15

Max Range: 3.4340. Min Range: -3.4340

Max Act: 2.9774. Min Act: 0.0000

Data Index: 46076 (The Pile)

Max Activating Token Index: 746

Text #16

Max Range: 3.4340. Min Range: -3.4340

Max Act: 2.9693. Min Act: -0.0000

Data Index: 76869 (The Pile)

Max Activating Token Index: 550

Text #17

Max Range: 3.4340. Min Range: -3.4340

Max Act: 2.9978. Min Act: 0.0000

Data Index: 881768 (The Pile)

Max Activating Token Index: 1011

Text #18

Max Range: 3.4340. Min Range: -3.4340

Max Act: 2.9981. Min Act: 0.0000

Data Index: 1420257 (The Pile)

Max Activating Token Index: 885

Text #19

Max Range: 3.4340. Min Range: -3.4340

Max Act: 3.0945. Min Act: 0.0000

Data Index: 1635239 (The Pile)

Max Activating Token Index: 938