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

Dataset: The Pile

Neuron 1642 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: 1.0101. Min Range: -1.0101

Max Act: 1.0101. Min Act: -0.0000

Data Index: 1462504 (The Pile)

Max Activating Token Index: 1011

Text #1

Max Range: 1.0101. Min Range: -1.0101

Max Act: 0.9626. Min Act: -0.0000

Data Index: 869747 (The Pile)

Max Activating Token Index: 948

Text #2

Max Range: 1.0101. Min Range: -1.0101

Max Act: 0.9754. Min Act: -0.0001

Data Index: 1501374 (The Pile)

Max Activating Token Index: 293

Text #3

Max Range: 1.0101. Min Range: -1.0101

Max Act: 0.8484. Min Act: -0.0000

Data Index: 902376 (The Pile)

Max Activating Token Index: 995

Text #4

Max Range: 1.0101. Min Range: -1.0101

Max Act: 0.8984. Min Act: -0.0001

Data Index: 402073 (The Pile)

Max Activating Token Index: 279

Text #5

Max Range: 1.0101. Min Range: -1.0101

Max Act: 0.8389. Min Act: -0.0000

Data Index: 1935619 (The Pile)

Max Activating Token Index: 898

Text #6

Max Range: 1.0101. Min Range: -1.0101

Max Act: 0.7573. Min Act: -0.0000

Data Index: 917965 (The Pile)

Max Activating Token Index: 349

Text #7

Max Range: 1.0101. Min Range: -1.0101

Max Act: 0.8092. Min Act: -0.0000

Data Index: 935211 (The Pile)

Max Activating Token Index: 683

Text #8

Max Range: 1.0101. Min Range: -1.0101

Max Act: 0.9060. Min Act: -0.0000

Data Index: 1244824 (The Pile)

Max Activating Token Index: 671

Text #9

Max Range: 1.0101. Min Range: -1.0101

Max Act: 0.8371. Min Act: -0.0000

Data Index: 1010968 (The Pile)

Max Activating Token Index: 536

Text #10

Max Range: 1.0101. Min Range: -1.0101

Max Act: 0.7421. Min Act: -0.0000

Data Index: 54564 (The Pile)

Max Activating Token Index: 660

Text #11

Max Range: 1.0101. Min Range: -1.0101

Max Act: 0.7643. Min Act: -0.0001

Data Index: 116718 (The Pile)

Max Activating Token Index: 456

Text #12

Max Range: 1.0101. Min Range: -1.0101

Max Act: 0.8493. Min Act: -0.0000

Data Index: 807649 (The Pile)

Max Activating Token Index: 242

Text #13

Max Range: 1.0101. Min Range: -1.0101

Max Act: 0.8008. Min Act: -0.0000

Data Index: 1001070 (The Pile)

Max Activating Token Index: 1013

Text #14

Max Range: 1.0101. Min Range: -1.0101

Max Act: 0.7547. Min Act: -0.0000

Data Index: 224131 (The Pile)

Max Activating Token Index: 190

Text #15

Max Range: 1.0101. Min Range: -1.0101

Max Act: 0.7362. Min Act: -0.0000

Data Index: 1275432 (The Pile)

Max Activating Token Index: 314

Text #16

Max Range: 1.0101. Min Range: -1.0101

Max Act: 0.8329. Min Act: -0.0000

Data Index: 1165220 (The Pile)

Max Activating Token Index: 968

Text #17

Max Range: 1.0101. Min Range: -1.0101

Max Act: 0.7667. Min Act: -0.0001

Data Index: 310155 (The Pile)

Max Activating Token Index: 325

Text #18

Max Range: 1.0101. Min Range: -1.0101

Max Act: 0.7533. Min Act: -0.0000

Data Index: 315592 (The Pile)

Max Activating Token Index: 162

Text #19

Max Range: 1.0101. Min Range: -1.0101

Max Act: 0.7190. Min Act: -0.0000

Data Index: 377354 (The Pile)

Max Activating Token Index: 694