Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 2884 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.4140. Min Range: -0.4140

Max Act: 0.3672. Min Act: -0.0000

Data Index: 1807910 (The Pile)

Max Activating Token Index: 61

Text #1

Max Range: 0.4140. Min Range: -0.4140

Max Act: 0.4000. Min Act: -0.0000

Data Index: 1381728 (The Pile)

Max Activating Token Index: 244

Text #2

Max Range: 0.4140. Min Range: -0.4140

Max Act: 0.3961. Min Act: -0.0000

Data Index: 1322688 (The Pile)

Max Activating Token Index: 495

Text #3

Max Range: 0.4140. Min Range: -0.4140

Max Act: 0.4140. Min Act: -0.0000

Data Index: 1264879 (The Pile)

Max Activating Token Index: 373

Text #4

Max Range: 0.4140. Min Range: -0.4140

Max Act: 0.3819. Min Act: -0.0000

Data Index: 1891825 (The Pile)

Max Activating Token Index: 366

Text #5

Max Range: 0.4140. Min Range: -0.4140

Max Act: 0.3661. Min Act: -0.0000

Data Index: 1904079 (The Pile)

Max Activating Token Index: 481

Text #6

Max Range: 0.4140. Min Range: -0.4140

Max Act: 0.3650. Min Act: -0.0000

Data Index: 474390 (The Pile)

Max Activating Token Index: 434

Text #7

Max Range: 0.4140. Min Range: -0.4140

Max Act: 0.3638. Min Act: -0.0000

Data Index: 1115836 (The Pile)

Max Activating Token Index: 76

Text #8

Max Range: 0.4140. Min Range: -0.4140

Max Act: 0.3561. Min Act: -0.0000

Data Index: 255965 (The Pile)

Max Activating Token Index: 395

Text #9

Max Range: 0.4140. Min Range: -0.4140

Max Act: 0.3833. Min Act: -0.0000

Data Index: 1066103 (The Pile)

Max Activating Token Index: 186

Text #10

Max Range: 0.4140. Min Range: -0.4140

Max Act: 0.3816. Min Act: -0.0000

Data Index: 329222 (The Pile)

Max Activating Token Index: 344

Text #11

Max Range: 0.4140. Min Range: -0.4140

Max Act: 0.4083. Min Act: -0.0000

Data Index: 985580 (The Pile)

Max Activating Token Index: 654

Text #12

Max Range: 0.4140. Min Range: -0.4140

Max Act: 0.3545. Min Act: -0.0000

Data Index: 369576 (The Pile)

Max Activating Token Index: 332

Text #13

Max Range: 0.4140. Min Range: -0.4140

Max Act: 0.3640. Min Act: -0.0000

Data Index: 586931 (The Pile)

Max Activating Token Index: 273

Text #14

Max Range: 0.4140. Min Range: -0.4140

Max Act: 0.3616. Min Act: -0.0000

Data Index: 899589 (The Pile)

Max Activating Token Index: 167

Text #15

Max Range: 0.4140. Min Range: -0.4140

Max Act: 0.3484. Min Act: -0.0000

Data Index: 1010931 (The Pile)

Max Activating Token Index: 127

Text #16

Max Range: 0.4140. Min Range: -0.4140

Max Act: 0.3443. Min Act: -0.0000

Data Index: 1701086 (The Pile)

Max Activating Token Index: 19

Text #17

Max Range: 0.4140. Min Range: -0.4140

Max Act: 0.3291. Min Act: -0.0000

Data Index: 211468 (The Pile)

Max Activating Token Index: 633

Text #18

Max Range: 0.4140. Min Range: -0.4140

Max Act: 0.3263. Min Act: -0.0000

Data Index: 1669267 (The Pile)

Max Activating Token Index: 1012

Text #19

Max Range: 0.4140. Min Range: -0.4140

Max Act: 0.3248. Min Act: -0.0000

Data Index: 1167453 (The Pile)

Max Activating Token Index: 137