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

Dataset: The Pile

Neuron 2450 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: 4.9340. Min Range: -4.9340

Max Act: 4.9340. Min Act: -0.0000

Data Index: 1325557 (The Pile)

Max Activating Token Index: 381

Text #1

Max Range: 4.9340. Min Range: -4.9340

Max Act: 3.5992. Min Act: -0.0000

Data Index: 1341779 (The Pile)

Max Activating Token Index: 13

Text #2

Max Range: 4.9340. Min Range: -4.9340

Max Act: 3.6257. Min Act: -0.0000

Data Index: 1018418 (The Pile)

Max Activating Token Index: 956

Text #3

Max Range: 4.9340. Min Range: -4.9340

Max Act: 3.4535. Min Act: -0.0000

Data Index: 1971867 (The Pile)

Max Activating Token Index: 100

Text #4

Max Range: 4.9340. Min Range: -4.9340

Max Act: 3.4006. Min Act: -0.0000

Data Index: 590334 (The Pile)

Max Activating Token Index: 356

Text #5

Max Range: 4.9340. Min Range: -4.9340

Max Act: 3.3432. Min Act: -0.0000

Data Index: 1146699 (The Pile)

Max Activating Token Index: 690

Text #6

Max Range: 4.9340. Min Range: -4.9340

Max Act: 3.1548. Min Act: -0.0000

Data Index: 352410 (The Pile)

Max Activating Token Index: 141

Text #7

Max Range: 4.9340. Min Range: -4.9340

Max Act: 3.4256. Min Act: -0.0000

Data Index: 520638 (The Pile)

Max Activating Token Index: 40

Text #8

Max Range: 4.9340. Min Range: -4.9340

Max Act: 3.2402. Min Act: -0.0000

Data Index: 1539167 (The Pile)

Max Activating Token Index: 125

Text #9

Max Range: 4.9340. Min Range: -4.9340

Max Act: 3.1082. Min Act: -0.0000

Data Index: 585688 (The Pile)

Max Activating Token Index: 1000

Text #10

Max Range: 4.9340. Min Range: -4.9340

Max Act: 3.1475. Min Act: -0.0000

Data Index: 1368701 (The Pile)

Max Activating Token Index: 789

Text #11

Max Range: 4.9340. Min Range: -4.9340

Max Act: 3.1796. Min Act: -0.0000

Data Index: 1629732 (The Pile)

Max Activating Token Index: 589

Text #12

Max Range: 4.9340. Min Range: -4.9340

Max Act: 3.1279. Min Act: -0.0000

Data Index: 1920141 (The Pile)

Max Activating Token Index: 246

Text #13

Max Range: 4.9340. Min Range: -4.9340

Max Act: 3.0602. Min Act: -0.0000

Data Index: 416835 (The Pile)

Max Activating Token Index: 209

Text #14

Max Range: 4.9340. Min Range: -4.9340

Max Act: 2.8728. Min Act: -0.0000

Data Index: 730092 (The Pile)

Max Activating Token Index: 584

Text #15

Max Range: 4.9340. Min Range: -4.9340

Max Act: 2.9685. Min Act: -0.0000

Data Index: 1034741 (The Pile)

Max Activating Token Index: 922

Text #16

Max Range: 4.9340. Min Range: -4.9340

Max Act: 2.8900. Min Act: -0.0000

Data Index: 1418778 (The Pile)

Max Activating Token Index: 353

Text #17

Max Range: 4.9340. Min Range: -4.9340

Max Act: 2.8707. Min Act: -0.0000

Data Index: 1234329 (The Pile)

Max Activating Token Index: 545

Text #18

Max Range: 4.9340. Min Range: -4.9340

Max Act: 2.9845. Min Act: -0.0000

Data Index: 1604510 (The Pile)

Max Activating Token Index: 49

Text #19

Max Range: 4.9340. Min Range: -4.9340

Max Act: 2.6960. Min Act: -0.0000

Data Index: 1771136 (The Pile)

Max Activating Token Index: 94