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

Dataset: The Pile

Neuron 1027 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1371. Min Range: -3.1371

Max Act: 3.1371. Min Act: -0.0000

Data Index: 1714476 (The Pile)

Max Activating Token Index: 161

Text #1

Max Range: 3.1371. Min Range: -3.1371

Max Act: 2.7099. Min Act: -0.0000

Data Index: 103819 (The Pile)

Max Activating Token Index: 488

Text #2

Max Range: 3.1371. Min Range: -3.1371

Max Act: 2.6068. Min Act: -0.0000

Data Index: 1593291 (The Pile)

Max Activating Token Index: 633

Text #3

Max Range: 3.1371. Min Range: -3.1371

Max Act: 2.4620. Min Act: -0.0000

Data Index: 1412709 (The Pile)

Max Activating Token Index: 576

Text #4

Max Range: 3.1371. Min Range: -3.1371

Max Act: 2.5761. Min Act: -0.0000

Data Index: 1341520 (The Pile)

Max Activating Token Index: 398

Text #5

Max Range: 3.1371. Min Range: -3.1371

Max Act: 2.2721. Min Act: -0.0000

Data Index: 452740 (The Pile)

Max Activating Token Index: 432

Text #6

Max Range: 3.1371. Min Range: -3.1371

Max Act: 2.3828. Min Act: -0.0000

Data Index: 1512108 (The Pile)

Max Activating Token Index: 909

Text #7

Max Range: 3.1371. Min Range: -3.1371

Max Act: 2.2568. Min Act: -0.0000

Data Index: 1069831 (The Pile)

Max Activating Token Index: 919

Text #8

Max Range: 3.1371. Min Range: -3.1371

Max Act: 2.3267. Min Act: -0.0000

Data Index: 592850 (The Pile)

Max Activating Token Index: 437

Text #9

Max Range: 3.1371. Min Range: -3.1371

Max Act: 2.2903. Min Act: -0.0000

Data Index: 216838 (The Pile)

Max Activating Token Index: 323

Text #10

Max Range: 3.1371. Min Range: -3.1371

Max Act: 2.2378. Min Act: -0.0000

Data Index: 496021 (The Pile)

Max Activating Token Index: 433

Text #11

Max Range: 3.1371. Min Range: -3.1371

Max Act: 2.1167. Min Act: -0.0000

Data Index: 823295 (The Pile)

Max Activating Token Index: 880

Text #12

Max Range: 3.1371. Min Range: -3.1371

Max Act: 2.2169. Min Act: -0.0000

Data Index: 153633 (The Pile)

Max Activating Token Index: 397

Text #13

Max Range: 3.1371. Min Range: -3.1371

Max Act: 2.2023. Min Act: -0.0000

Data Index: 977228 (The Pile)

Max Activating Token Index: 802

Text #14

Max Range: 3.1371. Min Range: -3.1371

Max Act: 2.1965. Min Act: -0.0000

Data Index: 926651 (The Pile)

Max Activating Token Index: 603

Text #15

Max Range: 3.1371. Min Range: -3.1371

Max Act: 2.0690. Min Act: -0.0000

Data Index: 1668217 (The Pile)

Max Activating Token Index: 851

Text #16

Max Range: 3.1371. Min Range: -3.1371

Max Act: 2.1726. Min Act: -0.0000

Data Index: 403427 (The Pile)

Max Activating Token Index: 295

Text #17

Max Range: 3.1371. Min Range: -3.1371

Max Act: 2.0393. Min Act: -0.0000

Data Index: 1321095 (The Pile)

Max Activating Token Index: 211

Text #18

Max Range: 3.1371. Min Range: -3.1371

Max Act: 2.0390. Min Act: -0.0000

Data Index: 1599867 (The Pile)

Max Activating Token Index: 812

Text #19

Max Range: 3.1371. Min Range: -3.1371

Max Act: 2.0453. Min Act: -0.0000

Data Index: 243795 (The Pile)

Max Activating Token Index: 121