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

Dataset: The Pile

Neuron 4630 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.3042. Min Range: -1.3042

Max Act: 1.2163. Min Act: -0.0000

Data Index: 345204 (The Pile)

Max Activating Token Index: 973

Text #1

Max Range: 1.3042. Min Range: -1.3042

Max Act: 1.3042. Min Act: -0.0000

Data Index: 196690 (The Pile)

Max Activating Token Index: 890

Text #2

Max Range: 1.3042. Min Range: -1.3042

Max Act: 1.2895. Min Act: -0.0000

Data Index: 1616322 (The Pile)

Max Activating Token Index: 137

Text #3

Max Range: 1.3042. Min Range: -1.3042

Max Act: 1.1806. Min Act: -0.0000

Data Index: 1037474 (The Pile)

Max Activating Token Index: 145

Text #4

Max Range: 1.3042. Min Range: -1.3042

Max Act: 1.1390. Min Act: -0.0000

Data Index: 1037761 (The Pile)

Max Activating Token Index: 117

Text #5

Max Range: 1.3042. Min Range: -1.3042

Max Act: 1.2104. Min Act: -0.0000

Data Index: 446485 (The Pile)

Max Activating Token Index: 687

Text #6

Max Range: 1.3042. Min Range: -1.3042

Max Act: 1.1178. Min Act: -0.0000

Data Index: 924924 (The Pile)

Max Activating Token Index: 971

Text #7

Max Range: 1.3042. Min Range: -1.3042

Max Act: 1.0713. Min Act: -0.0000

Data Index: 1303422 (The Pile)

Max Activating Token Index: 47

Text #8

Max Range: 1.3042. Min Range: -1.3042

Max Act: 1.0590. Min Act: -0.0000

Data Index: 403339 (The Pile)

Max Activating Token Index: 286

Text #9

Max Range: 1.3042. Min Range: -1.3042

Max Act: 1.0997. Min Act: -0.0000

Data Index: 144351 (The Pile)

Max Activating Token Index: 876

Text #10

Max Range: 1.3042. Min Range: -1.3042

Max Act: 1.1219. Min Act: -0.0000

Data Index: 1052693 (The Pile)

Max Activating Token Index: 456

Text #11

Max Range: 1.3042. Min Range: -1.3042

Max Act: 1.0570. Min Act: -0.0000

Data Index: 578226 (The Pile)

Max Activating Token Index: 383

Text #12

Max Range: 1.3042. Min Range: -1.3042

Max Act: 1.1532. Min Act: -0.0000

Data Index: 1546756 (The Pile)

Max Activating Token Index: 707

Text #13

Max Range: 1.3042. Min Range: -1.3042

Max Act: 1.0797. Min Act: -0.0000

Data Index: 961337 (The Pile)

Max Activating Token Index: 921

Text #14

Max Range: 1.3042. Min Range: -1.3042

Max Act: 1.0772. Min Act: -0.0000

Data Index: 1623822 (The Pile)

Max Activating Token Index: 998

Text #15

Max Range: 1.3042. Min Range: -1.3042

Max Act: 1.1046. Min Act: -0.0000

Data Index: 524567 (The Pile)

Max Activating Token Index: 551

Text #16

Max Range: 1.3042. Min Range: -1.3042

Max Act: 1.0535. Min Act: -0.0000

Data Index: 437656 (The Pile)

Max Activating Token Index: 884

Text #17

Max Range: 1.3042. Min Range: -1.3042

Max Act: 1.0905. Min Act: -0.0000

Data Index: 1639407 (The Pile)

Max Activating Token Index: 246

Text #18

Max Range: 1.3042. Min Range: -1.3042

Max Act: 1.0955. Min Act: -0.0000

Data Index: 1248396 (The Pile)

Max Activating Token Index: 652

Text #19

Max Range: 1.3042. Min Range: -1.3042

Max Act: 1.0871. Min Act: -0.0000

Data Index: 2852 (The Pile)

Max Activating Token Index: 47