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

Dataset: The Pile

Neuron 1632 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: 0.1899. Min Range: -0.1899

Max Act: 0.1899. Min Act: -0.0000

Data Index: 780313 (The Pile)

Max Activating Token Index: 809

Text #1

Max Range: 0.1899. Min Range: -0.1899

Max Act: 0.1710. Min Act: -0.0000

Data Index: 687726 (The Pile)

Max Activating Token Index: 109

Text #2

Max Range: 0.1899. Min Range: -0.1899

Max Act: 0.1594. Min Act: -0.0000

Data Index: 1030521 (The Pile)

Max Activating Token Index: 653

Text #3

Max Range: 0.1899. Min Range: -0.1899

Max Act: 0.1508. Min Act: -0.0000

Data Index: 762602 (The Pile)

Max Activating Token Index: 340

Text #4

Max Range: 0.1899. Min Range: -0.1899

Max Act: 0.1614. Min Act: -0.0000

Data Index: 72348 (The Pile)

Max Activating Token Index: 771

Text #5

Max Range: 0.1899. Min Range: -0.1899

Max Act: 0.1371. Min Act: -0.0000

Data Index: 1687573 (The Pile)

Max Activating Token Index: 891

Text #6

Max Range: 0.1899. Min Range: -0.1899

Max Act: 0.1364. Min Act: -0.0000

Data Index: 1726836 (The Pile)

Max Activating Token Index: 952

Text #7

Max Range: 0.1899. Min Range: -0.1899

Max Act: 0.1199. Min Act: -0.0000

Data Index: 1259183 (The Pile)

Max Activating Token Index: 897

Text #8

Max Range: 0.1899. Min Range: -0.1899

Max Act: 0.1272. Min Act: -0.0000

Data Index: 365833 (The Pile)

Max Activating Token Index: 939

Text #9

Max Range: 0.1899. Min Range: -0.1899

Max Act: 0.1352. Min Act: -0.0000

Data Index: 799917 (The Pile)

Max Activating Token Index: 486

Text #10

Max Range: 0.1899. Min Range: -0.1899

Max Act: 0.1127. Min Act: -0.0000

Data Index: 848764 (The Pile)

Max Activating Token Index: 494

Text #11

Max Range: 0.1899. Min Range: -0.1899

Max Act: 0.1116. Min Act: -0.0000

Data Index: 917067 (The Pile)

Max Activating Token Index: 151

Text #12

Max Range: 0.1899. Min Range: -0.1899

Max Act: 0.1078. Min Act: -0.0000

Data Index: 391202 (The Pile)

Max Activating Token Index: 899

Text #13

Max Range: 0.1899. Min Range: -0.1899

Max Act: 0.1230. Min Act: -0.0000

Data Index: 1174588 (The Pile)

Max Activating Token Index: 942

Text #14

Max Range: 0.1899. Min Range: -0.1899

Max Act: 0.1200. Min Act: -0.0000

Data Index: 1105618 (The Pile)

Max Activating Token Index: 343

Text #15

Max Range: 0.1899. Min Range: -0.1899

Max Act: 0.1075. Min Act: -0.0000

Data Index: 408799 (The Pile)

Max Activating Token Index: 201

Text #16

Max Range: 0.1899. Min Range: -0.1899

Max Act: 0.1170. Min Act: -0.0000

Data Index: 116042 (The Pile)

Max Activating Token Index: 105

Text #17

Max Range: 0.1899. Min Range: -0.1899

Max Act: 0.1030. Min Act: -0.0000

Data Index: 1056029 (The Pile)

Max Activating Token Index: 160

Text #18

Max Range: 0.1899. Min Range: -0.1899

Max Act: 0.1049. Min Act: -0.0000

Data Index: 812707 (The Pile)

Max Activating Token Index: 583

Text #19

Max Range: 0.1899. Min Range: -0.1899

Max Act: 0.1015. Min Act: -0.0000

Data Index: 1967127 (The Pile)

Max Activating Token Index: 637