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

Dataset: The Pile

Neuron 1637 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: 1.5409. Min Range: -1.5409

Max Act: 1.5409. Min Act: -0.0000

Data Index: 1916644 (The Pile)

Max Activating Token Index: 669

Text #1

Max Range: 1.5409. Min Range: -1.5409

Max Act: 1.3929. Min Act: -0.0000

Data Index: 548555 (The Pile)

Max Activating Token Index: 317

Text #2

Max Range: 1.5409. Min Range: -1.5409

Max Act: 1.3240. Min Act: -0.0000

Data Index: 1142218 (The Pile)

Max Activating Token Index: 155

Text #3

Max Range: 1.5409. Min Range: -1.5409

Max Act: 1.4201. Min Act: -0.0000

Data Index: 396665 (The Pile)

Max Activating Token Index: 225

Text #4

Max Range: 1.5409. Min Range: -1.5409

Max Act: 1.1873. Min Act: -0.0000

Data Index: 259296 (The Pile)

Max Activating Token Index: 613

Text #5

Max Range: 1.5409. Min Range: -1.5409

Max Act: 1.2127. Min Act: -0.0000

Data Index: 1717895 (The Pile)

Max Activating Token Index: 530

Text #6

Max Range: 1.5409. Min Range: -1.5409

Max Act: 1.2707. Min Act: -0.0000

Data Index: 1025024 (The Pile)

Max Activating Token Index: 226

Text #7

Max Range: 1.5409. Min Range: -1.5409

Max Act: 1.3473. Min Act: -0.0000

Data Index: 1780807 (The Pile)

Max Activating Token Index: 788

Text #8

Max Range: 1.5409. Min Range: -1.5409

Max Act: 1.3010. Min Act: -0.0000

Data Index: 1222186 (The Pile)

Max Activating Token Index: 470

Text #9

Max Range: 1.5409. Min Range: -1.5409

Max Act: 1.0388. Min Act: -0.0000

Data Index: 1765792 (The Pile)

Max Activating Token Index: 603

Text #10

Max Range: 1.5409. Min Range: -1.5409

Max Act: 1.0749. Min Act: -0.0000

Data Index: 1202533 (The Pile)

Max Activating Token Index: 167

Text #11

Max Range: 1.5409. Min Range: -1.5409

Max Act: 1.1186. Min Act: -0.0000

Data Index: 1127659 (The Pile)

Max Activating Token Index: 12

Text #12

Max Range: 1.5409. Min Range: -1.5409

Max Act: 1.1702. Min Act: -0.0000

Data Index: 1050016 (The Pile)

Max Activating Token Index: 789

Text #13

Max Range: 1.5409. Min Range: -1.5409

Max Act: 1.2614. Min Act: -0.0000

Data Index: 1399385 (The Pile)

Max Activating Token Index: 295

Text #14

Max Range: 1.5409. Min Range: -1.5409

Max Act: 1.2208. Min Act: -0.0000

Data Index: 1413864 (The Pile)

Max Activating Token Index: 501

Text #15

Max Range: 1.5409. Min Range: -1.5409

Max Act: 1.1417. Min Act: -0.0000

Data Index: 462508 (The Pile)

Max Activating Token Index: 267

Text #16

Max Range: 1.5409. Min Range: -1.5409

Max Act: 1.2304. Min Act: -0.0000

Data Index: 1666567 (The Pile)

Max Activating Token Index: 315

Text #17

Max Range: 1.5409. Min Range: -1.5409

Max Act: 1.0933. Min Act: -0.0000

Data Index: 1830938 (The Pile)

Max Activating Token Index: 639

Text #18

Max Range: 1.5409. Min Range: -1.5409

Max Act: 1.0475. Min Act: -0.0000

Data Index: 1555557 (The Pile)

Max Activating Token Index: 623

Text #19

Max Range: 1.5409. Min Range: -1.5409

Max Act: 1.0572. Min Act: -0.0000

Data Index: 1333158 (The Pile)

Max Activating Token Index: 858