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

Dataset: The Pile

Neuron 2473 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: 1.6404. Min Range: -1.6404

Max Act: 1.6404. Min Act: -0.0000

Data Index: 1484327 (The Pile)

Max Activating Token Index: 979

Text #1

Max Range: 1.6404. Min Range: -1.6404

Max Act: 1.4637. Min Act: -0.0000

Data Index: 1389122 (The Pile)

Max Activating Token Index: 620

Text #2

Max Range: 1.6404. Min Range: -1.6404

Max Act: 1.2013. Min Act: -0.0000

Data Index: 1107728 (The Pile)

Max Activating Token Index: 295

Text #3

Max Range: 1.6404. Min Range: -1.6404

Max Act: 1.1179. Min Act: -0.0000

Data Index: 1999795 (The Pile)

Max Activating Token Index: 926

Text #4

Max Range: 1.6404. Min Range: -1.6404

Max Act: 1.3228. Min Act: -0.0000

Data Index: 402126 (The Pile)

Max Activating Token Index: 506

Text #5

Max Range: 1.6404. Min Range: -1.6404

Max Act: 1.1786. Min Act: -0.0000

Data Index: 1079802 (The Pile)

Max Activating Token Index: 564

Text #6

Max Range: 1.6404. Min Range: -1.6404

Max Act: 1.2266. Min Act: -0.0000

Data Index: 1556030 (The Pile)

Max Activating Token Index: 21

Text #7

Max Range: 1.6404. Min Range: -1.6404

Max Act: 1.2121. Min Act: -0.0000

Data Index: 1146182 (The Pile)

Max Activating Token Index: 522

Text #8

Max Range: 1.6404. Min Range: -1.6404

Max Act: 1.2866. Min Act: -0.0000

Data Index: 1106739 (The Pile)

Max Activating Token Index: 190

Text #9

Max Range: 1.6404. Min Range: -1.6404

Max Act: 1.2838. Min Act: -0.0000

Data Index: 22096 (The Pile)

Max Activating Token Index: 272

Text #10

Max Range: 1.6404. Min Range: -1.6404

Max Act: 1.2661. Min Act: -0.0000

Data Index: 72100 (The Pile)

Max Activating Token Index: 468

Text #11

Max Range: 1.6404. Min Range: -1.6404

Max Act: 1.2702. Min Act: -0.0000

Data Index: 1933088 (The Pile)

Max Activating Token Index: 646

Text #12

Max Range: 1.6404. Min Range: -1.6404

Max Act: 1.2516. Min Act: -0.0000

Data Index: 1167759 (The Pile)

Max Activating Token Index: 896

Text #13

Max Range: 1.6404. Min Range: -1.6404

Max Act: 1.1032. Min Act: -0.0000

Data Index: 550787 (The Pile)

Max Activating Token Index: 847

Text #14

Max Range: 1.6404. Min Range: -1.6404

Max Act: 1.1456. Min Act: -0.0000

Data Index: 1945121 (The Pile)

Max Activating Token Index: 475

Text #15

Max Range: 1.6404. Min Range: -1.6404

Max Act: 1.1336. Min Act: -0.0000

Data Index: 780019 (The Pile)

Max Activating Token Index: 92

Text #16

Max Range: 1.6404. Min Range: -1.6404

Max Act: 1.1098. Min Act: -0.0000

Data Index: 326050 (The Pile)

Max Activating Token Index: 221

Text #17

Max Range: 1.6404. Min Range: -1.6404

Max Act: 1.0975. Min Act: -0.0000

Data Index: 1277218 (The Pile)

Max Activating Token Index: 455

Text #18

Max Range: 1.6404. Min Range: -1.6404

Max Act: 1.0931. Min Act: -0.0000

Data Index: 314235 (The Pile)

Max Activating Token Index: 25

Text #19

Max Range: 1.6404. Min Range: -1.6404

Max Act: 1.1595. Min Act: -0.0000

Data Index: 686426 (The Pile)

Max Activating Token Index: 32