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

Dataset: The Pile

Neuron 3238 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1786. Min Range: -1.1786

Max Act: 1.1786. Min Act: -0.0000

Data Index: 1952959 (The Pile)

Max Activating Token Index: 348

Text #1

Max Range: 1.1786. Min Range: -1.1786

Max Act: 1.1034. Min Act: -0.0000

Data Index: 753854 (The Pile)

Max Activating Token Index: 670

Text #2

Max Range: 1.1786. Min Range: -1.1786

Max Act: 0.8892. Min Act: -0.0000

Data Index: 1733957 (The Pile)

Max Activating Token Index: 738

Text #3

Max Range: 1.1786. Min Range: -1.1786

Max Act: 0.8397. Min Act: -0.0000

Data Index: 597636 (The Pile)

Max Activating Token Index: 110

Text #4

Max Range: 1.1786. Min Range: -1.1786

Max Act: 0.8565. Min Act: -0.0000

Data Index: 1969088 (The Pile)

Max Activating Token Index: 637

Text #5

Max Range: 1.1786. Min Range: -1.1786

Max Act: 0.8659. Min Act: -0.0000

Data Index: 840202 (The Pile)

Max Activating Token Index: 158

Text #6

Max Range: 1.1786. Min Range: -1.1786

Max Act: 0.9057. Min Act: -0.0000

Data Index: 381094 (The Pile)

Max Activating Token Index: 868

Text #7

Max Range: 1.1786. Min Range: -1.1786

Max Act: 0.7976. Min Act: -0.0000

Data Index: 1135948 (The Pile)

Max Activating Token Index: 451

Text #8

Max Range: 1.1786. Min Range: -1.1786

Max Act: 0.8379. Min Act: -0.0000

Data Index: 785558 (The Pile)

Max Activating Token Index: 735

Text #9

Max Range: 1.1786. Min Range: -1.1786

Max Act: 0.7779. Min Act: -0.0000

Data Index: 1580081 (The Pile)

Max Activating Token Index: 287

Text #10

Max Range: 1.1786. Min Range: -1.1786

Max Act: 0.8026. Min Act: -0.0000

Data Index: 812761 (The Pile)

Max Activating Token Index: 778

Text #11

Max Range: 1.1786. Min Range: -1.1786

Max Act: 0.7229. Min Act: -0.0000

Data Index: 28942 (The Pile)

Max Activating Token Index: 830

Text #12

Max Range: 1.1786. Min Range: -1.1786

Max Act: 0.7630. Min Act: -0.0000

Data Index: 1758861 (The Pile)

Max Activating Token Index: 977

Text #13

Max Range: 1.1786. Min Range: -1.1786

Max Act: 0.7011. Min Act: -0.0000

Data Index: 1572238 (The Pile)

Max Activating Token Index: 160

Text #14

Max Range: 1.1786. Min Range: -1.1786

Max Act: 0.7020. Min Act: -0.0000

Data Index: 86068 (The Pile)

Max Activating Token Index: 677

Text #15

Max Range: 1.1786. Min Range: -1.1786

Max Act: 0.7188. Min Act: -0.0000

Data Index: 1699383 (The Pile)

Max Activating Token Index: 732

Text #16

Max Range: 1.1786. Min Range: -1.1786

Max Act: 0.7443. Min Act: -0.0000

Data Index: 1409041 (The Pile)

Max Activating Token Index: 425

Text #17

Max Range: 1.1786. Min Range: -1.1786

Max Act: 0.6991. Min Act: -0.0000

Data Index: 681264 (The Pile)

Max Activating Token Index: 938

Text #18

Max Range: 1.1786. Min Range: -1.1786

Max Act: 0.7698. Min Act: -0.0000

Data Index: 1287080 (The Pile)

Max Activating Token Index: 933

Text #19

Max Range: 1.1786. Min Range: -1.1786

Max Act: 0.7166. Min Act: -0.0000

Data Index: 521596 (The Pile)

Max Activating Token Index: 26