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

Dataset: The Pile

Neuron 3076 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: 1.3338. Min Range: -1.3338

Max Act: 1.2096. Min Act: -0.0000

Data Index: 1041770 (The Pile)

Max Activating Token Index: 734

Text #1

Max Range: 1.3338. Min Range: -1.3338

Max Act: 1.1329. Min Act: -0.0000

Data Index: 821575 (The Pile)

Max Activating Token Index: 49

Text #2

Max Range: 1.3338. Min Range: -1.3338

Max Act: 1.1267. Min Act: -0.0001

Data Index: 889266 (The Pile)

Max Activating Token Index: 586

Text #3

Max Range: 1.3338. Min Range: -1.3338

Max Act: 1.1840. Min Act: -0.0000

Data Index: 1508920 (The Pile)

Max Activating Token Index: 22

Text #4

Max Range: 1.3338. Min Range: -1.3338

Max Act: 1.3338. Min Act: -0.0000

Data Index: 1226822 (The Pile)

Max Activating Token Index: 876

Text #5

Max Range: 1.3338. Min Range: -1.3338

Max Act: 1.1650. Min Act: -0.0000

Data Index: 495915 (The Pile)

Max Activating Token Index: 71

Text #6

Max Range: 1.3338. Min Range: -1.3338

Max Act: 1.0888. Min Act: -0.0000

Data Index: 1578307 (The Pile)

Max Activating Token Index: 506

Text #7

Max Range: 1.3338. Min Range: -1.3338

Max Act: 0.9647. Min Act: -0.0000

Data Index: 1352998 (The Pile)

Max Activating Token Index: 108

Text #8

Max Range: 1.3338. Min Range: -1.3338

Max Act: 1.1491. Min Act: -0.0000

Data Index: 652220 (The Pile)

Max Activating Token Index: 987

Text #9

Max Range: 1.3338. Min Range: -1.3338

Max Act: 1.0230. Min Act: -0.0000

Data Index: 435633 (The Pile)

Max Activating Token Index: 421

Text #10

Max Range: 1.3338. Min Range: -1.3338

Max Act: 1.0846. Min Act: -0.0000

Data Index: 238221 (The Pile)

Max Activating Token Index: 142

Text #11

Max Range: 1.3338. Min Range: -1.3338

Max Act: 1.0799. Min Act: -0.0000

Data Index: 1563887 (The Pile)

Max Activating Token Index: 142

Text #12

Max Range: 1.3338. Min Range: -1.3338

Max Act: 1.1668. Min Act: -0.0000

Data Index: 1784916 (The Pile)

Max Activating Token Index: 640

Text #13

Max Range: 1.3338. Min Range: -1.3338

Max Act: 1.0603. Min Act: -0.0000

Data Index: 1901657 (The Pile)

Max Activating Token Index: 139

Text #14

Max Range: 1.3338. Min Range: -1.3338

Max Act: 0.9729. Min Act: -0.0000

Data Index: 580324 (The Pile)

Max Activating Token Index: 869

Text #15

Max Range: 1.3338. Min Range: -1.3338

Max Act: 0.9085. Min Act: -0.0000

Data Index: 746514 (The Pile)

Max Activating Token Index: 640

Text #16

Max Range: 1.3338. Min Range: -1.3338

Max Act: 1.0297. Min Act: -0.0000

Data Index: 581921 (The Pile)

Max Activating Token Index: 466

Text #17

Max Range: 1.3338. Min Range: -1.3338

Max Act: 1.0200. Min Act: -0.0000

Data Index: 467254 (The Pile)

Max Activating Token Index: 735

Text #18

Max Range: 1.3338. Min Range: -1.3338

Max Act: 1.1032. Min Act: -0.0000

Data Index: 512673 (The Pile)

Max Activating Token Index: 305

Text #19

Max Range: 1.3338. Min Range: -1.3338

Max Act: 1.0561. Min Act: -0.0000

Data Index: 1471337 (The Pile)

Max Activating Token Index: 368