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

Dataset: The Pile

Neuron 2755 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9340. Min Range: -1.9340

Max Act: 1.9340. Min Act: -0.0000

Data Index: 1084245 (The Pile)

Max Activating Token Index: 825

Text #1

Max Range: 1.9340. Min Range: -1.9340

Max Act: 1.1094. Min Act: -0.0000

Data Index: 860222 (The Pile)

Max Activating Token Index: 943

Text #2

Max Range: 1.9340. Min Range: -1.9340

Max Act: 1.0517. Min Act: 0.0000

Data Index: 1452014 (The Pile)

Max Activating Token Index: 224

Text #3

Max Range: 1.9340. Min Range: -1.9340

Max Act: 1.0476. Min Act: -0.0000

Data Index: 1231763 (The Pile)

Max Activating Token Index: 568

Text #4

Max Range: 1.9340. Min Range: -1.9340

Max Act: 1.0445. Min Act: -0.0000

Data Index: 725239 (The Pile)

Max Activating Token Index: 407

Text #5

Max Range: 1.9340. Min Range: -1.9340

Max Act: 1.0260. Min Act: -0.0000

Data Index: 578083 (The Pile)

Max Activating Token Index: 28

Text #6

Max Range: 1.9340. Min Range: -1.9340

Max Act: 1.0148. Min Act: -0.0000

Data Index: 1175479 (The Pile)

Max Activating Token Index: 770

Text #7

Max Range: 1.9340. Min Range: -1.9340

Max Act: 1.1406. Min Act: -0.0000

Data Index: 1786442 (The Pile)

Max Activating Token Index: 828

Text #8

Max Range: 1.9340. Min Range: -1.9340

Max Act: 0.9951. Min Act: -0.0000

Data Index: 1200973 (The Pile)

Max Activating Token Index: 1011

Text #9

Max Range: 1.9340. Min Range: -1.9340

Max Act: 0.9888. Min Act: -0.0000

Data Index: 1621904 (The Pile)

Max Activating Token Index: 738

Text #10

Max Range: 1.9340. Min Range: -1.9340

Max Act: 0.8998. Min Act: -0.0000

Data Index: 123011 (The Pile)

Max Activating Token Index: 170

Text #11

Max Range: 1.9340. Min Range: -1.9340

Max Act: 0.9440. Min Act: -0.0000

Data Index: 1963420 (The Pile)

Max Activating Token Index: 718

Text #12

Max Range: 1.9340. Min Range: -1.9340

Max Act: 0.8347. Min Act: -0.0000

Data Index: 737858 (The Pile)

Max Activating Token Index: 750

Text #13

Max Range: 1.9340. Min Range: -1.9340

Max Act: 0.9109. Min Act: -0.0000

Data Index: 584867 (The Pile)

Max Activating Token Index: 96

Text #14

Max Range: 1.9340. Min Range: -1.9340

Max Act: 0.9144. Min Act: -0.0000

Data Index: 787019 (The Pile)

Max Activating Token Index: 858

Text #15

Max Range: 1.9340. Min Range: -1.9340

Max Act: 0.9475. Min Act: -0.0000

Data Index: 236558 (The Pile)

Max Activating Token Index: 425

Text #16

Max Range: 1.9340. Min Range: -1.9340

Max Act: 0.8956. Min Act: -0.0000

Data Index: 849077 (The Pile)

Max Activating Token Index: 183

Text #17

Max Range: 1.9340. Min Range: -1.9340

Max Act: 1.0082. Min Act: -0.0000

Data Index: 1424396 (The Pile)

Max Activating Token Index: 163

Text #18

Max Range: 1.9340. Min Range: -1.9340

Max Act: 0.9006. Min Act: -0.0000

Data Index: 87338 (The Pile)

Max Activating Token Index: 573

Text #19

Max Range: 1.9340. Min Range: -1.9340

Max Act: 0.8597. Min Act: -0.0000

Data Index: 327275 (The Pile)

Max Activating Token Index: 636