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

Dataset: The Pile

Neuron 4541 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5850. Min Range: -1.5850

Max Act: 1.5714. Min Act: -0.0000

Data Index: 762981 (The Pile)

Max Activating Token Index: 890

Text #1

Max Range: 1.5850. Min Range: -1.5850

Max Act: 1.5850. Min Act: -0.0000

Data Index: 575355 (The Pile)

Max Activating Token Index: 335

Text #2

Max Range: 1.5850. Min Range: -1.5850

Max Act: 1.5295. Min Act: -0.0000

Data Index: 1319716 (The Pile)

Max Activating Token Index: 858

Text #3

Max Range: 1.5850. Min Range: -1.5850

Max Act: 1.5601. Min Act: -0.0000

Data Index: 934330 (The Pile)

Max Activating Token Index: 1005

Text #4

Max Range: 1.5850. Min Range: -1.5850

Max Act: 1.3960. Min Act: -0.0000

Data Index: 358708 (The Pile)

Max Activating Token Index: 972

Text #5

Max Range: 1.5850. Min Range: -1.5850

Max Act: 1.4653. Min Act: -0.0000

Data Index: 917883 (The Pile)

Max Activating Token Index: 317

Text #6

Max Range: 1.5850. Min Range: -1.5850

Max Act: 1.4498. Min Act: -0.0000

Data Index: 626374 (The Pile)

Max Activating Token Index: 151

Text #7

Max Range: 1.5850. Min Range: -1.5850

Max Act: 1.4228. Min Act: -0.0000

Data Index: 384067 (The Pile)

Max Activating Token Index: 791

Text #8

Max Range: 1.5850. Min Range: -1.5850

Max Act: 1.3366. Min Act: -0.0000

Data Index: 990545 (The Pile)

Max Activating Token Index: 224

Text #9

Max Range: 1.5850. Min Range: -1.5850

Max Act: 1.3339. Min Act: -0.0000

Data Index: 703528 (The Pile)

Max Activating Token Index: 667

Text #10

Max Range: 1.5850. Min Range: -1.5850

Max Act: 1.4074. Min Act: -0.0000

Data Index: 89697 (The Pile)

Max Activating Token Index: 821

Text #11

Max Range: 1.5850. Min Range: -1.5850

Max Act: 1.3172. Min Act: -0.0000

Data Index: 1298730 (The Pile)

Max Activating Token Index: 970

Text #12

Max Range: 1.5850. Min Range: -1.5850

Max Act: 1.3371. Min Act: -0.0000

Data Index: 1094996 (The Pile)

Max Activating Token Index: 706

Text #13

Max Range: 1.5850. Min Range: -1.5850

Max Act: 1.3384. Min Act: -0.0000

Data Index: 331824 (The Pile)

Max Activating Token Index: 890

Text #14

Max Range: 1.5850. Min Range: -1.5850

Max Act: 1.3049. Min Act: -0.0000

Data Index: 422283 (The Pile)

Max Activating Token Index: 616

Text #15

Max Range: 1.5850. Min Range: -1.5850

Max Act: 1.3311. Min Act: -0.0000

Data Index: 701564 (The Pile)

Max Activating Token Index: 491

Text #16

Max Range: 1.5850. Min Range: -1.5850

Max Act: 1.3203. Min Act: -0.0000

Data Index: 842537 (The Pile)

Max Activating Token Index: 934

Text #17

Max Range: 1.5850. Min Range: -1.5850

Max Act: 1.3032. Min Act: -0.0000

Data Index: 1493498 (The Pile)

Max Activating Token Index: 269

Text #18

Max Range: 1.5850. Min Range: -1.5850

Max Act: 1.3776. Min Act: -0.0000

Data Index: 125447 (The Pile)

Max Activating Token Index: 639

Text #19

Max Range: 1.5850. Min Range: -1.5850

Max Act: 1.3044. Min Act: -0.0000

Data Index: 1280291 (The Pile)

Max Activating Token Index: 442