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

Dataset: The Pile

Neuron 2747 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: 1.6404. Min Range: -1.6404

Max Act: 1.6404. Min Act: -0.0000

Data Index: 1119423 (The Pile)

Max Activating Token Index: 241

Text #1

Max Range: 1.6404. Min Range: -1.6404

Max Act: 1.1987. Min Act: -0.0000

Data Index: 682718 (The Pile)

Max Activating Token Index: 128

Text #2

Max Range: 1.6404. Min Range: -1.6404

Max Act: 1.2432. Min Act: -0.0000

Data Index: 1228606 (The Pile)

Max Activating Token Index: 409

Text #3

Max Range: 1.6404. Min Range: -1.6404

Max Act: 1.2256. Min Act: -0.0000

Data Index: 1776939 (The Pile)

Max Activating Token Index: 696

Text #4

Max Range: 1.6404. Min Range: -1.6404

Max Act: 1.1962. Min Act: -0.0000

Data Index: 83477 (The Pile)

Max Activating Token Index: 97

Text #5

Max Range: 1.6404. Min Range: -1.6404

Max Act: 1.1863. Min Act: -0.0000

Data Index: 1950483 (The Pile)

Max Activating Token Index: 365

Text #6

Max Range: 1.6404. Min Range: -1.6404

Max Act: 1.1096. Min Act: -0.0000

Data Index: 1297977 (The Pile)

Max Activating Token Index: 200

Text #7

Max Range: 1.6404. Min Range: -1.6404

Max Act: 1.1252. Min Act: -0.0000

Data Index: 900405 (The Pile)

Max Activating Token Index: 175

Text #8

Max Range: 1.6404. Min Range: -1.6404

Max Act: 1.1296. Min Act: -0.0000

Data Index: 14372 (The Pile)

Max Activating Token Index: 538

Text #9

Max Range: 1.6404. Min Range: -1.6404

Max Act: 1.0400. Min Act: -0.0000

Data Index: 1599579 (The Pile)

Max Activating Token Index: 488

Text #10

Max Range: 1.6404. Min Range: -1.6404

Max Act: 1.0737. Min Act: -0.0000

Data Index: 1022690 (The Pile)

Max Activating Token Index: 729

Text #11

Max Range: 1.6404. Min Range: -1.6404

Max Act: 1.0579. Min Act: -0.0000

Data Index: 128856 (The Pile)

Max Activating Token Index: 410

Text #12

Max Range: 1.6404. Min Range: -1.6404

Max Act: 1.1229. Min Act: -0.0000

Data Index: 250563 (The Pile)

Max Activating Token Index: 827

Text #13

Max Range: 1.6404. Min Range: -1.6404

Max Act: 1.0824. Min Act: -0.0000

Data Index: 917891 (The Pile)

Max Activating Token Index: 1022

Text #14

Max Range: 1.6404. Min Range: -1.6404

Max Act: 1.0449. Min Act: -0.0000

Data Index: 823272 (The Pile)

Max Activating Token Index: 15

Text #15

Max Range: 1.6404. Min Range: -1.6404

Max Act: 0.9699. Min Act: -0.0000

Data Index: 602299 (The Pile)

Max Activating Token Index: 120

Text #16

Max Range: 1.6404. Min Range: -1.6404

Max Act: 0.9948. Min Act: -0.0000

Data Index: 1956534 (The Pile)

Max Activating Token Index: 618

Text #17

Max Range: 1.6404. Min Range: -1.6404

Max Act: 0.9881. Min Act: -0.0000

Data Index: 541104 (The Pile)

Max Activating Token Index: 982

Text #18

Max Range: 1.6404. Min Range: -1.6404

Max Act: 1.0396. Min Act: -0.0000

Data Index: 488889 (The Pile)

Max Activating Token Index: 340

Text #19

Max Range: 1.6404. Min Range: -1.6404

Max Act: 1.0075. Min Act: -0.0000

Data Index: 250079 (The Pile)

Max Activating Token Index: 726