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

Dataset: The Pile

Neuron 2083 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5837. Min Range: -0.5837

Max Act: 0.5837. Min Act: -0.0000

Data Index: 510684 (The Pile)

Max Activating Token Index: 475

Text #1

Max Range: 0.5837. Min Range: -0.5837

Max Act: 0.5367. Min Act: -0.0000

Data Index: 208888 (The Pile)

Max Activating Token Index: 290

Text #2

Max Range: 0.5837. Min Range: -0.5837

Max Act: 0.5531. Min Act: -0.0000

Data Index: 264808 (The Pile)

Max Activating Token Index: 73

Text #3

Max Range: 0.5837. Min Range: -0.5837

Max Act: 0.5178. Min Act: -0.0000

Data Index: 1332495 (The Pile)

Max Activating Token Index: 968

Text #4

Max Range: 0.5837. Min Range: -0.5837

Max Act: 0.4324. Min Act: -0.0000

Data Index: 856046 (The Pile)

Max Activating Token Index: 287

Text #5

Max Range: 0.5837. Min Range: -0.5837

Max Act: 0.4118. Min Act: -0.0000

Data Index: 505877 (The Pile)

Max Activating Token Index: 769

Text #6

Max Range: 0.5837. Min Range: -0.5837

Max Act: 0.3958. Min Act: -0.0000

Data Index: 424385 (The Pile)

Max Activating Token Index: 557

Text #7

Max Range: 0.5837. Min Range: -0.5837

Max Act: 0.4886. Min Act: -0.0000

Data Index: 389034 (The Pile)

Max Activating Token Index: 908

Text #8

Max Range: 0.5837. Min Range: -0.5837

Max Act: 0.4244. Min Act: -0.0000

Data Index: 1189863 (The Pile)

Max Activating Token Index: 566

Text #9

Max Range: 0.5837. Min Range: -0.5837

Max Act: 0.4080. Min Act: -0.0000

Data Index: 251415 (The Pile)

Max Activating Token Index: 869

Text #10

Max Range: 0.5837. Min Range: -0.5837

Max Act: 0.4058. Min Act: -0.0000

Data Index: 1947751 (The Pile)

Max Activating Token Index: 460

Text #11

Max Range: 0.5837. Min Range: -0.5837

Max Act: 0.3763. Min Act: -0.0000

Data Index: 680205 (The Pile)

Max Activating Token Index: 96

Text #12

Max Range: 0.5837. Min Range: -0.5837

Max Act: 0.3946. Min Act: -0.0000

Data Index: 787402 (The Pile)

Max Activating Token Index: 189

Text #13

Max Range: 0.5837. Min Range: -0.5837

Max Act: 0.3911. Min Act: -0.0000

Data Index: 1206429 (The Pile)

Max Activating Token Index: 382

Text #14

Max Range: 0.5837. Min Range: -0.5837

Max Act: 0.3142. Min Act: -0.0000

Data Index: 867777 (The Pile)

Max Activating Token Index: 29

Text #15

Max Range: 0.5837. Min Range: -0.5837

Max Act: 0.4069. Min Act: -0.0000

Data Index: 873142 (The Pile)

Max Activating Token Index: 997

Text #16

Max Range: 0.5837. Min Range: -0.5837

Max Act: 0.3417. Min Act: -0.0000

Data Index: 1195807 (The Pile)

Max Activating Token Index: 585

Text #17

Max Range: 0.5837. Min Range: -0.5837

Max Act: 0.3692. Min Act: -0.0000

Data Index: 1732212 (The Pile)

Max Activating Token Index: 488

Text #18

Max Range: 0.5837. Min Range: -0.5837

Max Act: 0.3126. Min Act: -0.0000

Data Index: 1874209 (The Pile)

Max Activating Token Index: 289

Text #19

Max Range: 0.5837. Min Range: -0.5837

Max Act: 0.3267. Min Act: -0.0000

Data Index: 768683 (The Pile)

Max Activating Token Index: 657