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

Dataset: The Pile

Neuron 4033 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: 4.0024. Min Range: -4.0024

Max Act: 3.5273. Min Act: -0.0000

Data Index: 490239 (The Pile)

Max Activating Token Index: 827

Text #1

Max Range: 4.0024. Min Range: -4.0024

Max Act: 4.0024. Min Act: -0.0000

Data Index: 714391 (The Pile)

Max Activating Token Index: 740

Text #2

Max Range: 4.0024. Min Range: -4.0024

Max Act: 3.3211. Min Act: -0.0000

Data Index: 1214851 (The Pile)

Max Activating Token Index: 809

Text #3

Max Range: 4.0024. Min Range: -4.0024

Max Act: 3.5651. Min Act: -0.0000

Data Index: 1023115 (The Pile)

Max Activating Token Index: 623

Text #4

Max Range: 4.0024. Min Range: -4.0024

Max Act: 3.2992. Min Act: -0.0000

Data Index: 1585331 (The Pile)

Max Activating Token Index: 833

Text #5

Max Range: 4.0024. Min Range: -4.0024

Max Act: 3.2649. Min Act: -0.0000

Data Index: 527931 (The Pile)

Max Activating Token Index: 774

Text #6

Max Range: 4.0024. Min Range: -4.0024

Max Act: 2.9502. Min Act: -0.0000

Data Index: 1596012 (The Pile)

Max Activating Token Index: 877

Text #7

Max Range: 4.0024. Min Range: -4.0024

Max Act: 3.5273. Min Act: -0.0000

Data Index: 92445 (The Pile)

Max Activating Token Index: 829

Text #8

Max Range: 4.0024. Min Range: -4.0024

Max Act: 2.9018. Min Act: -0.0000

Data Index: 224791 (The Pile)

Max Activating Token Index: 383

Text #9

Max Range: 4.0024. Min Range: -4.0024

Max Act: 3.3282. Min Act: -0.0000

Data Index: 1772707 (The Pile)

Max Activating Token Index: 163

Text #10

Max Range: 4.0024. Min Range: -4.0024

Max Act: 3.1728. Min Act: -0.0000

Data Index: 1301542 (The Pile)

Max Activating Token Index: 43

Text #11

Max Range: 4.0024. Min Range: -4.0024

Max Act: 3.0115. Min Act: -0.0000

Data Index: 1123344 (The Pile)

Max Activating Token Index: 590

Text #12

Max Range: 4.0024. Min Range: -4.0024

Max Act: 2.9727. Min Act: -0.0000

Data Index: 1764150 (The Pile)

Max Activating Token Index: 633

Text #13

Max Range: 4.0024. Min Range: -4.0024

Max Act: 3.0964. Min Act: -0.0000

Data Index: 712007 (The Pile)

Max Activating Token Index: 532

Text #14

Max Range: 4.0024. Min Range: -4.0024

Max Act: 2.9536. Min Act: -0.0000

Data Index: 1951486 (The Pile)

Max Activating Token Index: 595

Text #15

Max Range: 4.0024. Min Range: -4.0024

Max Act: 2.9132. Min Act: -0.0000

Data Index: 1959651 (The Pile)

Max Activating Token Index: 385

Text #16

Max Range: 4.0024. Min Range: -4.0024

Max Act: 2.9167. Min Act: -0.0000

Data Index: 1674777 (The Pile)

Max Activating Token Index: 989

Text #17

Max Range: 4.0024. Min Range: -4.0024

Max Act: 2.7483. Min Act: -0.0000

Data Index: 364405 (The Pile)

Max Activating Token Index: 670

Text #18

Max Range: 4.0024. Min Range: -4.0024

Max Act: 2.9018. Min Act: -0.0000

Data Index: 1546397 (The Pile)

Max Activating Token Index: 481

Text #19

Max Range: 4.0024. Min Range: -4.0024

Max Act: 3.0048. Min Act: -0.0000

Data Index: 1318124 (The Pile)

Max Activating Token Index: 474