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

Dataset: The Pile

Neuron 1184 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: 0.9936. Min Range: -0.9936

Max Act: 0.9936. Min Act: -0.0000

Data Index: 1361898 (The Pile)

Max Activating Token Index: 335

Text #1

Max Range: 0.9936. Min Range: -0.9936

Max Act: 0.9280. Min Act: -0.0000

Data Index: 1782776 (The Pile)

Max Activating Token Index: 824

Text #2

Max Range: 0.9936. Min Range: -0.9936

Max Act: 0.9868. Min Act: -0.0000

Data Index: 1994003 (The Pile)

Max Activating Token Index: 284

Text #3

Max Range: 0.9936. Min Range: -0.9936

Max Act: 0.9332. Min Act: -0.0000

Data Index: 1872485 (The Pile)

Max Activating Token Index: 325

Text #4

Max Range: 0.9936. Min Range: -0.9936

Max Act: 0.8991. Min Act: -0.0000

Data Index: 538043 (The Pile)

Max Activating Token Index: 312

Text #5

Max Range: 0.9936. Min Range: -0.9936

Max Act: 0.8822. Min Act: -0.0000

Data Index: 595209 (The Pile)

Max Activating Token Index: 381

Text #6

Max Range: 0.9936. Min Range: -0.9936

Max Act: 0.8549. Min Act: -0.0000

Data Index: 1246908 (The Pile)

Max Activating Token Index: 654

Text #7

Max Range: 0.9936. Min Range: -0.9936

Max Act: 0.7305. Min Act: -0.0000

Data Index: 414904 (The Pile)

Max Activating Token Index: 622

Text #8

Max Range: 0.9936. Min Range: -0.9936

Max Act: 0.8169. Min Act: -0.0000

Data Index: 306617 (The Pile)

Max Activating Token Index: 108

Text #9

Max Range: 0.9936. Min Range: -0.9936

Max Act: 0.7935. Min Act: -0.0000

Data Index: 1327850 (The Pile)

Max Activating Token Index: 37

Text #10

Max Range: 0.9936. Min Range: -0.9936

Max Act: 0.7587. Min Act: -0.0000

Data Index: 1131981 (The Pile)

Max Activating Token Index: 462

Text #11

Max Range: 0.9936. Min Range: -0.9936

Max Act: 0.7840. Min Act: -0.0000

Data Index: 463890 (The Pile)

Max Activating Token Index: 555

Text #12

Max Range: 0.9936. Min Range: -0.9936

Max Act: 0.7281. Min Act: -0.0000

Data Index: 1474824 (The Pile)

Max Activating Token Index: 117

Text #13

Max Range: 0.9936. Min Range: -0.9936

Max Act: 0.7564. Min Act: -0.0000

Data Index: 1838804 (The Pile)

Max Activating Token Index: 21

Text #14

Max Range: 0.9936. Min Range: -0.9936

Max Act: 0.7042. Min Act: -0.0000

Data Index: 1413810 (The Pile)

Max Activating Token Index: 172

Text #15

Max Range: 0.9936. Min Range: -0.9936

Max Act: 0.7206. Min Act: -0.0000

Data Index: 663537 (The Pile)

Max Activating Token Index: 261

Text #16

Max Range: 0.9936. Min Range: -0.9936

Max Act: 0.6956. Min Act: -0.0000

Data Index: 1389231 (The Pile)

Max Activating Token Index: 85

Text #17

Max Range: 0.9936. Min Range: -0.9936

Max Act: 0.7263. Min Act: -0.0000

Data Index: 1714728 (The Pile)

Max Activating Token Index: 643

Text #18

Max Range: 0.9936. Min Range: -0.9936

Max Act: 0.7512. Min Act: -0.0000

Data Index: 1528994 (The Pile)

Max Activating Token Index: 584

Text #19

Max Range: 0.9936. Min Range: -0.9936

Max Act: 0.7309. Min Act: -0.0000

Data Index: 392774 (The Pile)

Max Activating Token Index: 597