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

Dataset: The Pile

Neuron 1790 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: 1.2796. Min Range: -1.2796

Max Act: 1.2796. Min Act: -0.0000

Data Index: 1441264 (The Pile)

Max Activating Token Index: 628

Text #1

Max Range: 1.2796. Min Range: -1.2796

Max Act: 1.2094. Min Act: -0.0000

Data Index: 773958 (The Pile)

Max Activating Token Index: 423

Text #2

Max Range: 1.2796. Min Range: -1.2796

Max Act: 1.2794. Min Act: -0.0000

Data Index: 482121 (The Pile)

Max Activating Token Index: 749

Text #3

Max Range: 1.2796. Min Range: -1.2796

Max Act: 1.2694. Min Act: -0.0000

Data Index: 1542214 (The Pile)

Max Activating Token Index: 295

Text #4

Max Range: 1.2796. Min Range: -1.2796

Max Act: 1.1552. Min Act: -0.0000

Data Index: 1798941 (The Pile)

Max Activating Token Index: 683

Text #5

Max Range: 1.2796. Min Range: -1.2796

Max Act: 1.1037. Min Act: -0.0000

Data Index: 1555561 (The Pile)

Max Activating Token Index: 544

Text #6

Max Range: 1.2796. Min Range: -1.2796

Max Act: 1.2273. Min Act: -0.0000

Data Index: 1406271 (The Pile)

Max Activating Token Index: 818

Text #7

Max Range: 1.2796. Min Range: -1.2796

Max Act: 1.2281. Min Act: -0.0000

Data Index: 1725995 (The Pile)

Max Activating Token Index: 543

Text #8

Max Range: 1.2796. Min Range: -1.2796

Max Act: 1.1519. Min Act: -0.0000

Data Index: 1465119 (The Pile)

Max Activating Token Index: 207

Text #9

Max Range: 1.2796. Min Range: -1.2796

Max Act: 1.0928. Min Act: -0.0000

Data Index: 597988 (The Pile)

Max Activating Token Index: 747

Text #10

Max Range: 1.2796. Min Range: -1.2796

Max Act: 1.2020. Min Act: -0.0000

Data Index: 1481974 (The Pile)

Max Activating Token Index: 532

Text #11

Max Range: 1.2796. Min Range: -1.2796

Max Act: 1.1927. Min Act: -0.0000

Data Index: 1946914 (The Pile)

Max Activating Token Index: 361

Text #12

Max Range: 1.2796. Min Range: -1.2796

Max Act: 1.2016. Min Act: -0.0000

Data Index: 938042 (The Pile)

Max Activating Token Index: 727

Text #13

Max Range: 1.2796. Min Range: -1.2796

Max Act: 1.1013. Min Act: -0.0000

Data Index: 1705634 (The Pile)

Max Activating Token Index: 65

Text #14

Max Range: 1.2796. Min Range: -1.2796

Max Act: 1.1678. Min Act: -0.0000

Data Index: 274469 (The Pile)

Max Activating Token Index: 715

Text #15

Max Range: 1.2796. Min Range: -1.2796

Max Act: 1.0973. Min Act: -0.0000

Data Index: 107657 (The Pile)

Max Activating Token Index: 736

Text #16

Max Range: 1.2796. Min Range: -1.2796

Max Act: 1.0998. Min Act: -0.0000

Data Index: 1995250 (The Pile)

Max Activating Token Index: 786

Text #17

Max Range: 1.2796. Min Range: -1.2796

Max Act: 1.0617. Min Act: -0.0000

Data Index: 952105 (The Pile)

Max Activating Token Index: 475

Text #18

Max Range: 1.2796. Min Range: -1.2796

Max Act: 1.0503. Min Act: -0.0000

Data Index: 1294795 (The Pile)

Max Activating Token Index: 774

Text #19

Max Range: 1.2796. Min Range: -1.2796

Max Act: 1.0672. Min Act: -0.0000

Data Index: 847192 (The Pile)

Max Activating Token Index: 449