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

Dataset: The Pile

Neuron 1817 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: 5.8821. Min Range: -5.8821

Max Act: 5.8821. Min Act: -0.0000

Data Index: 1942805 (The Pile)

Max Activating Token Index: 964

Text #1

Max Range: 5.8821. Min Range: -5.8821

Max Act: 4.9705. Min Act: -0.0000

Data Index: 1142 (The Pile)

Max Activating Token Index: 708

Text #2

Max Range: 5.8821. Min Range: -5.8821

Max Act: 5.5203. Min Act: -0.0000

Data Index: 1443255 (The Pile)

Max Activating Token Index: 706

Text #3

Max Range: 5.8821. Min Range: -5.8821

Max Act: 5.1087. Min Act: -0.0000

Data Index: 60132 (The Pile)

Max Activating Token Index: 714

Text #4

Max Range: 5.8821. Min Range: -5.8821

Max Act: 5.2233. Min Act: -0.0000

Data Index: 1436454 (The Pile)

Max Activating Token Index: 756

Text #5

Max Range: 5.8821. Min Range: -5.8821

Max Act: 5.2889. Min Act: -0.0000

Data Index: 1861232 (The Pile)

Max Activating Token Index: 758

Text #6

Max Range: 5.8821. Min Range: -5.8821

Max Act: 5.0682. Min Act: -0.0000

Data Index: 313028 (The Pile)

Max Activating Token Index: 587

Text #7

Max Range: 5.8821. Min Range: -5.8821

Max Act: 4.8375. Min Act: -0.0000

Data Index: 145592 (The Pile)

Max Activating Token Index: 473

Text #8

Max Range: 5.8821. Min Range: -5.8821

Max Act: 4.5965. Min Act: -0.0000

Data Index: 757959 (The Pile)

Max Activating Token Index: 435

Text #9

Max Range: 5.8821. Min Range: -5.8821

Max Act: 4.6236. Min Act: -0.0000

Data Index: 661239 (The Pile)

Max Activating Token Index: 654

Text #10

Max Range: 5.8821. Min Range: -5.8821

Max Act: 3.6018. Min Act: -0.0000

Data Index: 118602 (The Pile)

Max Activating Token Index: 233

Text #11

Max Range: 5.8821. Min Range: -5.8821

Max Act: 3.6351. Min Act: -0.0000

Data Index: 1060113 (The Pile)

Max Activating Token Index: 286

Text #12

Max Range: 5.8821. Min Range: -5.8821

Max Act: 3.6951. Min Act: -0.0000

Data Index: 1045891 (The Pile)

Max Activating Token Index: 253

Text #13

Max Range: 5.8821. Min Range: -5.8821

Max Act: 2.8171. Min Act: -0.0000

Data Index: 271523 (The Pile)

Max Activating Token Index: 998

Text #14

Max Range: 5.8821. Min Range: -5.8821

Max Act: 2.7168. Min Act: -0.0000

Data Index: 1344383 (The Pile)

Max Activating Token Index: 838

Text #15

Max Range: 5.8821. Min Range: -5.8821

Max Act: 2.7939. Min Act: -0.0000

Data Index: 197931 (The Pile)

Max Activating Token Index: 528

Text #16

Max Range: 5.8821. Min Range: -5.8821

Max Act: 2.7603. Min Act: -0.0000

Data Index: 544877 (The Pile)

Max Activating Token Index: 817

Text #17

Max Range: 5.8821. Min Range: -5.8821

Max Act: 3.0054. Min Act: -0.0000

Data Index: 257023 (The Pile)

Max Activating Token Index: 933

Text #18

Max Range: 5.8821. Min Range: -5.8821

Max Act: 2.7059. Min Act: -0.0000

Data Index: 547478 (The Pile)

Max Activating Token Index: 199

Text #19

Max Range: 5.8821. Min Range: -5.8821

Max Act: 2.6119. Min Act: -0.0000

Data Index: 255640 (The Pile)

Max Activating Token Index: 207