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

Dataset: The Pile

Neuron 2882 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: 0.8005. Min Range: -0.8005

Max Act: 0.7574. Min Act: -0.0000

Data Index: 1296044 (The Pile)

Max Activating Token Index: 87

Text #1

Max Range: 0.8005. Min Range: -0.8005

Max Act: 0.8005. Min Act: -0.0000

Data Index: 677958 (The Pile)

Max Activating Token Index: 795

Text #2

Max Range: 0.8005. Min Range: -0.8005

Max Act: 0.7437. Min Act: -0.0000

Data Index: 936210 (The Pile)

Max Activating Token Index: 515

Text #3

Max Range: 0.8005. Min Range: -0.8005

Max Act: 0.6233. Min Act: -0.0000

Data Index: 121042 (The Pile)

Max Activating Token Index: 630

Text #4

Max Range: 0.8005. Min Range: -0.8005

Max Act: 0.7174. Min Act: -0.0000

Data Index: 1218 (The Pile)

Max Activating Token Index: 886

Text #5

Max Range: 0.8005. Min Range: -0.8005

Max Act: 0.7023. Min Act: -0.0000

Data Index: 298272 (The Pile)

Max Activating Token Index: 706

Text #6

Max Range: 0.8005. Min Range: -0.8005

Max Act: 0.6758. Min Act: -0.0000

Data Index: 195347 (The Pile)

Max Activating Token Index: 54

Text #7

Max Range: 0.8005. Min Range: -0.8005

Max Act: 0.6148. Min Act: -0.0000

Data Index: 533930 (The Pile)

Max Activating Token Index: 560

Text #8

Max Range: 0.8005. Min Range: -0.8005

Max Act: 0.7086. Min Act: -0.0000

Data Index: 1155631 (The Pile)

Max Activating Token Index: 667

Text #9

Max Range: 0.8005. Min Range: -0.8005

Max Act: 0.6391. Min Act: -0.0000

Data Index: 1615529 (The Pile)

Max Activating Token Index: 270

Text #10

Max Range: 0.8005. Min Range: -0.8005

Max Act: 0.6007. Min Act: -0.0000

Data Index: 245335 (The Pile)

Max Activating Token Index: 452

Text #11

Max Range: 0.8005. Min Range: -0.8005

Max Act: 0.6618. Min Act: -0.0000

Data Index: 1838354 (The Pile)

Max Activating Token Index: 393

Text #12

Max Range: 0.8005. Min Range: -0.8005

Max Act: 0.6594. Min Act: -0.0000

Data Index: 1569278 (The Pile)

Max Activating Token Index: 383

Text #13

Max Range: 0.8005. Min Range: -0.8005

Max Act: 0.6260. Min Act: -0.0000

Data Index: 1683333 (The Pile)

Max Activating Token Index: 495

Text #14

Max Range: 0.8005. Min Range: -0.8005

Max Act: 0.6073. Min Act: -0.0000

Data Index: 812985 (The Pile)

Max Activating Token Index: 481

Text #15

Max Range: 0.8005. Min Range: -0.8005

Max Act: 0.6289. Min Act: -0.0000

Data Index: 1156942 (The Pile)

Max Activating Token Index: 184

Text #16

Max Range: 0.8005. Min Range: -0.8005

Max Act: 0.6629. Min Act: -0.0000

Data Index: 1345346 (The Pile)

Max Activating Token Index: 986

Text #17

Max Range: 0.8005. Min Range: -0.8005

Max Act: 0.6033. Min Act: -0.0000

Data Index: 628719 (The Pile)

Max Activating Token Index: 357

Text #18

Max Range: 0.8005. Min Range: -0.8005

Max Act: 0.6003. Min Act: -0.0000

Data Index: 1329779 (The Pile)

Max Activating Token Index: 380

Text #19

Max Range: 0.8005. Min Range: -0.8005

Max Act: 0.5991. Min Act: -0.0000

Data Index: 1788718 (The Pile)

Max Activating Token Index: 801