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

Dataset: The Pile

Neuron 2560 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: 1.6156. Min Range: -1.6156

Max Act: 1.6156. Min Act: -0.0000

Data Index: 121146 (The Pile)

Max Activating Token Index: 619

Text #1

Max Range: 1.6156. Min Range: -1.6156

Max Act: 1.5274. Min Act: -0.0000

Data Index: 1218058 (The Pile)

Max Activating Token Index: 805

Text #2

Max Range: 1.6156. Min Range: -1.6156

Max Act: 1.3852. Min Act: -0.0000

Data Index: 1689943 (The Pile)

Max Activating Token Index: 573

Text #3

Max Range: 1.6156. Min Range: -1.6156

Max Act: 1.0926. Min Act: -0.0000

Data Index: 1650503 (The Pile)

Max Activating Token Index: 659

Text #4

Max Range: 1.6156. Min Range: -1.6156

Max Act: 0.9697. Min Act: -0.0000

Data Index: 1581841 (The Pile)

Max Activating Token Index: 821

Text #5

Max Range: 1.6156. Min Range: -1.6156

Max Act: 1.0073. Min Act: -0.0000

Data Index: 1564403 (The Pile)

Max Activating Token Index: 445

Text #6

Max Range: 1.6156. Min Range: -1.6156

Max Act: 1.0591. Min Act: -0.0000

Data Index: 961124 (The Pile)

Max Activating Token Index: 279

Text #7

Max Range: 1.6156. Min Range: -1.6156

Max Act: 0.8401. Min Act: -0.0000

Data Index: 1005772 (The Pile)

Max Activating Token Index: 525

Text #8

Max Range: 1.6156. Min Range: -1.6156

Max Act: 0.9085. Min Act: -0.0000

Data Index: 1647214 (The Pile)

Max Activating Token Index: 56

Text #9

Max Range: 1.6156. Min Range: -1.6156

Max Act: 0.8413. Min Act: -0.0000

Data Index: 1271401 (The Pile)

Max Activating Token Index: 536

Text #10

Max Range: 1.6156. Min Range: -1.6156

Max Act: 0.8881. Min Act: -0.0000

Data Index: 1236790 (The Pile)

Max Activating Token Index: 451

Text #11

Max Range: 1.6156. Min Range: -1.6156

Max Act: 0.9045. Min Act: -0.0000

Data Index: 864376 (The Pile)

Max Activating Token Index: 540

Text #12

Max Range: 1.6156. Min Range: -1.6156

Max Act: 0.8121. Min Act: -0.0000

Data Index: 1038811 (The Pile)

Max Activating Token Index: 602

Text #13

Max Range: 1.6156. Min Range: -1.6156

Max Act: 0.7780. Min Act: -0.0000

Data Index: 337148 (The Pile)

Max Activating Token Index: 834

Text #14

Max Range: 1.6156. Min Range: -1.6156

Max Act: 0.6159. Min Act: -0.0000

Data Index: 499497 (The Pile)

Max Activating Token Index: 942

Text #15

Max Range: 1.6156. Min Range: -1.6156

Max Act: 0.7837. Min Act: -0.0000

Data Index: 786631 (The Pile)

Max Activating Token Index: 368

Text #16

Max Range: 1.6156. Min Range: -1.6156

Max Act: 0.7545. Min Act: -0.0000

Data Index: 1011616 (The Pile)

Max Activating Token Index: 394

Text #17

Max Range: 1.6156. Min Range: -1.6156

Max Act: 0.8774. Min Act: -0.0000

Data Index: 1821304 (The Pile)

Max Activating Token Index: 891

Text #18

Max Range: 1.6156. Min Range: -1.6156

Max Act: 0.7399. Min Act: -0.0000

Data Index: 963075 (The Pile)

Max Activating Token Index: 456

Text #19

Max Range: 1.6156. Min Range: -1.6156

Max Act: 0.6921. Min Act: -0.0000

Data Index: 1815568 (The Pile)

Max Activating Token Index: 848