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

Dataset: The Pile

Neuron 633 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1006. Min Range: -1.1006

Max Act: 1.1006. Min Act: -0.0000

Data Index: 413902 (The Pile)

Max Activating Token Index: 849

Text #1

Max Range: 1.1006. Min Range: -1.1006

Max Act: 0.9192. Min Act: -0.0000

Data Index: 595244 (The Pile)

Max Activating Token Index: 749

Text #2

Max Range: 1.1006. Min Range: -1.1006

Max Act: 0.5199. Min Act: -0.0000

Data Index: 1623020 (The Pile)

Max Activating Token Index: 912

Text #3

Max Range: 1.1006. Min Range: -1.1006

Max Act: 0.5430. Min Act: -0.0000

Data Index: 634829 (The Pile)

Max Activating Token Index: 583

Text #4

Max Range: 1.1006. Min Range: -1.1006

Max Act: 0.5125. Min Act: -0.0000

Data Index: 1986848 (The Pile)

Max Activating Token Index: 797

Text #5

Max Range: 1.1006. Min Range: -1.1006

Max Act: 0.4961. Min Act: -0.0000

Data Index: 1584768 (The Pile)

Max Activating Token Index: 572

Text #6

Max Range: 1.1006. Min Range: -1.1006

Max Act: 0.4355. Min Act: -0.0000

Data Index: 1206595 (The Pile)

Max Activating Token Index: 284

Text #7

Max Range: 1.1006. Min Range: -1.1006

Max Act: 0.3991. Min Act: 0.0000

Data Index: 89726 (The Pile)

Max Activating Token Index: 665

Text #8

Max Range: 1.1006. Min Range: -1.1006

Max Act: 0.4073. Min Act: -0.0000

Data Index: 131155 (The Pile)

Max Activating Token Index: 780

Text #9

Max Range: 1.1006. Min Range: -1.1006

Max Act: 0.3273. Min Act: -0.0000

Data Index: 435620 (The Pile)

Max Activating Token Index: 579

Text #10

Max Range: 1.1006. Min Range: -1.1006

Max Act: 0.2391. Min Act: -0.0000

Data Index: 1765852 (The Pile)

Max Activating Token Index: 796

Text #11

Max Range: 1.1006. Min Range: -1.1006

Max Act: 0.3286. Min Act: -0.0000

Data Index: 1073296 (The Pile)

Max Activating Token Index: 781

Text #12

Max Range: 1.1006. Min Range: -1.1006

Max Act: 0.3269. Min Act: -0.0000

Data Index: 1779962 (The Pile)

Max Activating Token Index: 839

Text #13

Max Range: 1.1006. Min Range: -1.1006

Max Act: 0.3456. Min Act: -0.0000

Data Index: 1711386 (The Pile)

Max Activating Token Index: 940

Text #14

Max Range: 1.1006. Min Range: -1.1006

Max Act: 0.3004. Min Act: -0.0000

Data Index: 1112130 (The Pile)

Max Activating Token Index: 137

Text #15

Max Range: 1.1006. Min Range: -1.1006

Max Act: 0.3183. Min Act: 0.0000

Data Index: 1615155 (The Pile)

Max Activating Token Index: 287

Text #16

Max Range: 1.1006. Min Range: -1.1006

Max Act: 0.3008. Min Act: -0.0000

Data Index: 763180 (The Pile)

Max Activating Token Index: 837

Text #17

Max Range: 1.1006. Min Range: -1.1006

Max Act: 0.3134. Min Act: -0.0000

Data Index: 1962216 (The Pile)

Max Activating Token Index: 829

Text #18

Max Range: 1.1006. Min Range: -1.1006

Max Act: 0.3044. Min Act: -0.0000

Data Index: 931882 (The Pile)

Max Activating Token Index: 59

Text #19

Max Range: 1.1006. Min Range: -1.1006

Max Act: 0.3172. Min Act: -0.0000

Data Index: 1431644 (The Pile)

Max Activating Token Index: 862