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

Dataset: The Pile

Neuron 3001 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: 0.3491. Min Range: -0.3491

Max Act: 0.3491. Min Act: -0.0000

Data Index: 1845790 (The Pile)

Max Activating Token Index: 158

Text #1

Max Range: 0.3491. Min Range: -0.3491

Max Act: 0.3373. Min Act: -0.0000

Data Index: 233960 (The Pile)

Max Activating Token Index: 311

Text #2

Max Range: 0.3491. Min Range: -0.3491

Max Act: 0.3194. Min Act: -0.0000

Data Index: 437426 (The Pile)

Max Activating Token Index: 374

Text #3

Max Range: 0.3491. Min Range: -0.3491

Max Act: 0.3167. Min Act: -0.0000

Data Index: 1920611 (The Pile)

Max Activating Token Index: 156

Text #4

Max Range: 0.3491. Min Range: -0.3491

Max Act: 0.2938. Min Act: -0.0000

Data Index: 1797102 (The Pile)

Max Activating Token Index: 390

Text #5

Max Range: 0.3491. Min Range: -0.3491

Max Act: 0.2783. Min Act: -0.0000

Data Index: 1540584 (The Pile)

Max Activating Token Index: 120

Text #6

Max Range: 0.3491. Min Range: -0.3491

Max Act: 0.2915. Min Act: -0.0000

Data Index: 1801284 (The Pile)

Max Activating Token Index: 521

Text #7

Max Range: 0.3491. Min Range: -0.3491

Max Act: 0.2730. Min Act: -0.0000

Data Index: 1993369 (The Pile)

Max Activating Token Index: 274

Text #8

Max Range: 0.3491. Min Range: -0.3491

Max Act: 0.2664. Min Act: -0.0000

Data Index: 1211606 (The Pile)

Max Activating Token Index: 164

Text #9

Max Range: 0.3491. Min Range: -0.3491

Max Act: 0.2581. Min Act: -0.0000

Data Index: 535447 (The Pile)

Max Activating Token Index: 280

Text #10

Max Range: 0.3491. Min Range: -0.3491

Max Act: 0.2351. Min Act: -0.0000

Data Index: 1647544 (The Pile)

Max Activating Token Index: 595

Text #11

Max Range: 0.3491. Min Range: -0.3491

Max Act: 0.2478. Min Act: -0.0000

Data Index: 335986 (The Pile)

Max Activating Token Index: 350

Text #12

Max Range: 0.3491. Min Range: -0.3491

Max Act: 0.2664. Min Act: -0.0000

Data Index: 256777 (The Pile)

Max Activating Token Index: 170

Text #13

Max Range: 0.3491. Min Range: -0.3491

Max Act: 0.2436. Min Act: -0.0000

Data Index: 422089 (The Pile)

Max Activating Token Index: 565

Text #14

Max Range: 0.3491. Min Range: -0.3491

Max Act: 0.2451. Min Act: -0.0000

Data Index: 1874637 (The Pile)

Max Activating Token Index: 440

Text #15

Max Range: 0.3491. Min Range: -0.3491

Max Act: 0.2443. Min Act: -0.0000

Data Index: 659593 (The Pile)

Max Activating Token Index: 419

Text #16

Max Range: 0.3491. Min Range: -0.3491

Max Act: 0.2485. Min Act: -0.0000

Data Index: 1886786 (The Pile)

Max Activating Token Index: 339

Text #17

Max Range: 0.3491. Min Range: -0.3491

Max Act: 0.2365. Min Act: -0.0000

Data Index: 1500358 (The Pile)

Max Activating Token Index: 208

Text #18

Max Range: 0.3491. Min Range: -0.3491

Max Act: 0.2389. Min Act: -0.0000

Data Index: 1798916 (The Pile)

Max Activating Token Index: 691

Text #19

Max Range: 0.3491. Min Range: -0.3491

Max Act: 0.2358. Min Act: -0.0000

Data Index: 1291561 (The Pile)

Max Activating Token Index: 301