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

Dataset: The Pile

Neuron 2889 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.2049. Min Range: -5.2049

Max Act: 5.2049. Min Act: -0.0000

Data Index: 400833 (The Pile)

Max Activating Token Index: 842

Text #1

Max Range: 5.2049. Min Range: -5.2049

Max Act: 5.1745. Min Act: -0.0000

Data Index: 1523125 (The Pile)

Max Activating Token Index: 537

Text #2

Max Range: 5.2049. Min Range: -5.2049

Max Act: 5.1127. Min Act: -0.0000

Data Index: 776211 (The Pile)

Max Activating Token Index: 549

Text #3

Max Range: 5.2049. Min Range: -5.2049

Max Act: 4.6960. Min Act: -0.0000

Data Index: 925796 (The Pile)

Max Activating Token Index: 320

Text #4

Max Range: 5.2049. Min Range: -5.2049

Max Act: 4.6382. Min Act: -0.0000

Data Index: 709335 (The Pile)

Max Activating Token Index: 578

Text #5

Max Range: 5.2049. Min Range: -5.2049

Max Act: 4.4336. Min Act: -0.0000

Data Index: 4859 (The Pile)

Max Activating Token Index: 111

Text #6

Max Range: 5.2049. Min Range: -5.2049

Max Act: 4.3979. Min Act: -0.0000

Data Index: 1945435 (The Pile)

Max Activating Token Index: 872

Text #7

Max Range: 5.2049. Min Range: -5.2049

Max Act: 4.2594. Min Act: -0.0000

Data Index: 1992734 (The Pile)

Max Activating Token Index: 859

Text #8

Max Range: 5.2049. Min Range: -5.2049

Max Act: 4.0636. Min Act: -0.0000

Data Index: 1571654 (The Pile)

Max Activating Token Index: 435

Text #9

Max Range: 5.2049. Min Range: -5.2049

Max Act: 4.2599. Min Act: -0.0000

Data Index: 285264 (The Pile)

Max Activating Token Index: 883

Text #10

Max Range: 5.2049. Min Range: -5.2049

Max Act: 4.3662. Min Act: -0.0000

Data Index: 376653 (The Pile)

Max Activating Token Index: 842

Text #11

Max Range: 5.2049. Min Range: -5.2049

Max Act: 4.1959. Min Act: -0.0000

Data Index: 64310 (The Pile)

Max Activating Token Index: 585

Text #12

Max Range: 5.2049. Min Range: -5.2049

Max Act: 4.1671. Min Act: -0.0000

Data Index: 1514433 (The Pile)

Max Activating Token Index: 677

Text #13

Max Range: 5.2049. Min Range: -5.2049

Max Act: 4.1394. Min Act: -0.0000

Data Index: 1403826 (The Pile)

Max Activating Token Index: 867

Text #14

Max Range: 5.2049. Min Range: -5.2049

Max Act: 3.9710. Min Act: -0.0000

Data Index: 446209 (The Pile)

Max Activating Token Index: 384

Text #15

Max Range: 5.2049. Min Range: -5.2049

Max Act: 4.1266. Min Act: -0.0000

Data Index: 1983136 (The Pile)

Max Activating Token Index: 222

Text #16

Max Range: 5.2049. Min Range: -5.2049

Max Act: 4.1443. Min Act: -0.0000

Data Index: 792490 (The Pile)

Max Activating Token Index: 862

Text #17

Max Range: 5.2049. Min Range: -5.2049

Max Act: 4.0898. Min Act: -0.0000

Data Index: 1587880 (The Pile)

Max Activating Token Index: 546

Text #18

Max Range: 5.2049. Min Range: -5.2049

Max Act: 4.0877. Min Act: -0.0000

Data Index: 1593615 (The Pile)

Max Activating Token Index: 471

Text #19

Max Range: 5.2049. Min Range: -5.2049

Max Act: 4.2240. Min Act: -0.0000

Data Index: 363827 (The Pile)

Max Activating Token Index: 769