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

Dataset: The Pile

Neuron 374 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7014. Min Range: -1.7014

Max Act: 1.7014. Min Act: -0.0000

Data Index: 915835 (The Pile)

Max Activating Token Index: 977

Text #1

Max Range: 1.7014. Min Range: -1.7014

Max Act: 1.3939. Min Act: -0.0000

Data Index: 1372760 (The Pile)

Max Activating Token Index: 222

Text #2

Max Range: 1.7014. Min Range: -1.7014

Max Act: 1.4095. Min Act: -0.0000

Data Index: 1765181 (The Pile)

Max Activating Token Index: 481

Text #3

Max Range: 1.7014. Min Range: -1.7014

Max Act: 1.4782. Min Act: 0.0000

Data Index: 1768395 (The Pile)

Max Activating Token Index: 430

Text #4

Max Range: 1.7014. Min Range: -1.7014

Max Act: 1.3422. Min Act: 0.0001

Data Index: 124042 (The Pile)

Max Activating Token Index: 524

Text #5

Max Range: 1.7014. Min Range: -1.7014

Max Act: 1.4054. Min Act: -0.0000

Data Index: 1093991 (The Pile)

Max Activating Token Index: 359

Text #6

Max Range: 1.7014. Min Range: -1.7014

Max Act: 1.3024. Min Act: -0.0000

Data Index: 857650 (The Pile)

Max Activating Token Index: 914

Text #7

Max Range: 1.7014. Min Range: -1.7014

Max Act: 1.2134. Min Act: -0.0000

Data Index: 1900354 (The Pile)

Max Activating Token Index: 344

Text #8

Max Range: 1.7014. Min Range: -1.7014

Max Act: 1.2239. Min Act: -0.0000

Data Index: 858193 (The Pile)

Max Activating Token Index: 228

Text #9

Max Range: 1.7014. Min Range: -1.7014

Max Act: 1.2631. Min Act: 0.0000

Data Index: 1524060 (The Pile)

Max Activating Token Index: 514

Text #10

Max Range: 1.7014. Min Range: -1.7014

Max Act: 1.1473. Min Act: -0.0000

Data Index: 717630 (The Pile)

Max Activating Token Index: 417

Text #11

Max Range: 1.7014. Min Range: -1.7014

Max Act: 1.1543. Min Act: -0.0000

Data Index: 716949 (The Pile)

Max Activating Token Index: 397

Text #12

Max Range: 1.7014. Min Range: -1.7014

Max Act: 1.2730. Min Act: -0.0000

Data Index: 469980 (The Pile)

Max Activating Token Index: 446

Text #13

Max Range: 1.7014. Min Range: -1.7014

Max Act: 1.1587. Min Act: -0.0000

Data Index: 548362 (The Pile)

Max Activating Token Index: 264

Text #14

Max Range: 1.7014. Min Range: -1.7014

Max Act: 1.1901. Min Act: -0.0000

Data Index: 1744852 (The Pile)

Max Activating Token Index: 767

Text #15

Max Range: 1.7014. Min Range: -1.7014

Max Act: 1.1899. Min Act: -0.0000

Data Index: 1434539 (The Pile)

Max Activating Token Index: 659

Text #16

Max Range: 1.7014. Min Range: -1.7014

Max Act: 1.2155. Min Act: -0.0000

Data Index: 842480 (The Pile)

Max Activating Token Index: 989

Text #17

Max Range: 1.7014. Min Range: -1.7014

Max Act: 1.1812. Min Act: -0.0000

Data Index: 1210928 (The Pile)

Max Activating Token Index: 907

Text #18

Max Range: 1.7014. Min Range: -1.7014

Max Act: 1.1106. Min Act: 0.0000

Data Index: 1331738 (The Pile)

Max Activating Token Index: 907

Text #19

Max Range: 1.7014. Min Range: -1.7014

Max Act: 1.1384. Min Act: -0.0000

Data Index: 734007 (The Pile)

Max Activating Token Index: 578