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

Dataset: The Pile

Neuron 4579 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8792. Min Range: -0.8792

Max Act: 0.8792. Min Act: -0.0000

Data Index: 126618 (The Pile)

Max Activating Token Index: 846

Text #1

Max Range: 0.8792. Min Range: -0.8792

Max Act: 0.8658. Min Act: -0.0000

Data Index: 779716 (The Pile)

Max Activating Token Index: 313

Text #2

Max Range: 0.8792. Min Range: -0.8792

Max Act: 0.8148. Min Act: -0.0000

Data Index: 418337 (The Pile)

Max Activating Token Index: 160

Text #3

Max Range: 0.8792. Min Range: -0.8792

Max Act: 0.8050. Min Act: -0.0000

Data Index: 1601898 (The Pile)

Max Activating Token Index: 598

Text #4

Max Range: 0.8792. Min Range: -0.8792

Max Act: 0.8039. Min Act: -0.0000

Data Index: 189191 (The Pile)

Max Activating Token Index: 227

Text #5

Max Range: 0.8792. Min Range: -0.8792

Max Act: 0.7664. Min Act: -0.0000

Data Index: 185517 (The Pile)

Max Activating Token Index: 383

Text #6

Max Range: 0.8792. Min Range: -0.8792

Max Act: 0.8106. Min Act: -0.0000

Data Index: 1973301 (The Pile)

Max Activating Token Index: 918

Text #7

Max Range: 0.8792. Min Range: -0.8792

Max Act: 0.8048. Min Act: -0.0000

Data Index: 813073 (The Pile)

Max Activating Token Index: 425

Text #8

Max Range: 0.8792. Min Range: -0.8792

Max Act: 0.7860. Min Act: -0.0000

Data Index: 488200 (The Pile)

Max Activating Token Index: 370

Text #9

Max Range: 0.8792. Min Range: -0.8792

Max Act: 0.7339. Min Act: -0.0000

Data Index: 568571 (The Pile)

Max Activating Token Index: 156

Text #10

Max Range: 0.8792. Min Range: -0.8792

Max Act: 0.7577. Min Act: -0.0000

Data Index: 240758 (The Pile)

Max Activating Token Index: 422

Text #11

Max Range: 0.8792. Min Range: -0.8792

Max Act: 0.8241. Min Act: -0.0000

Data Index: 1415717 (The Pile)

Max Activating Token Index: 602

Text #12

Max Range: 0.8792. Min Range: -0.8792

Max Act: 0.7363. Min Act: -0.0000

Data Index: 1478619 (The Pile)

Max Activating Token Index: 820

Text #13

Max Range: 0.8792. Min Range: -0.8792

Max Act: 0.7430. Min Act: -0.0000

Data Index: 1173525 (The Pile)

Max Activating Token Index: 468

Text #14

Max Range: 0.8792. Min Range: -0.8792

Max Act: 0.7696. Min Act: -0.0000

Data Index: 551151 (The Pile)

Max Activating Token Index: 383

Text #15

Max Range: 0.8792. Min Range: -0.8792

Max Act: 0.7932. Min Act: -0.0000

Data Index: 331475 (The Pile)

Max Activating Token Index: 145

Text #16

Max Range: 0.8792. Min Range: -0.8792

Max Act: 0.7440. Min Act: -0.0000

Data Index: 1574597 (The Pile)

Max Activating Token Index: 346

Text #17

Max Range: 0.8792. Min Range: -0.8792

Max Act: 0.6964. Min Act: -0.0000

Data Index: 1802981 (The Pile)

Max Activating Token Index: 660

Text #18

Max Range: 0.8792. Min Range: -0.8792

Max Act: 0.7084. Min Act: -0.0000

Data Index: 521661 (The Pile)

Max Activating Token Index: 357

Text #19

Max Range: 0.8792. Min Range: -0.8792

Max Act: 0.7289. Min Act: -0.0000

Data Index: 142647 (The Pile)

Max Activating Token Index: 685