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

Dataset: The Pile

Neuron 3833 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8020. Min Range: -0.8020

Max Act: 0.7822. Min Act: -0.0000

Data Index: 7348 (The Pile)

Max Activating Token Index: 293

Text #1

Max Range: 0.8020. Min Range: -0.8020

Max Act: 0.7991. Min Act: -0.0000

Data Index: 577793 (The Pile)

Max Activating Token Index: 579

Text #2

Max Range: 0.8020. Min Range: -0.8020

Max Act: 0.8020. Min Act: -0.0000

Data Index: 1697560 (The Pile)

Max Activating Token Index: 209

Text #3

Max Range: 0.8020. Min Range: -0.8020

Max Act: 0.7734. Min Act: -0.0000

Data Index: 1551752 (The Pile)

Max Activating Token Index: 456

Text #4

Max Range: 0.8020. Min Range: -0.8020

Max Act: 0.7605. Min Act: -0.0000

Data Index: 1178727 (The Pile)

Max Activating Token Index: 549

Text #5

Max Range: 0.8020. Min Range: -0.8020

Max Act: 0.7313. Min Act: -0.0000

Data Index: 53051 (The Pile)

Max Activating Token Index: 388

Text #6

Max Range: 0.8020. Min Range: -0.8020

Max Act: 0.6662. Min Act: -0.0000

Data Index: 701287 (The Pile)

Max Activating Token Index: 614

Text #7

Max Range: 0.8020. Min Range: -0.8020

Max Act: 0.7439. Min Act: -0.0000

Data Index: 917910 (The Pile)

Max Activating Token Index: 210

Text #8

Max Range: 0.8020. Min Range: -0.8020

Max Act: 0.7437. Min Act: -0.0000

Data Index: 1899479 (The Pile)

Max Activating Token Index: 244

Text #9

Max Range: 0.8020. Min Range: -0.8020

Max Act: 0.7446. Min Act: -0.0000

Data Index: 1684822 (The Pile)

Max Activating Token Index: 171

Text #10

Max Range: 0.8020. Min Range: -0.8020

Max Act: 0.7383. Min Act: -0.0000

Data Index: 702806 (The Pile)

Max Activating Token Index: 472

Text #11

Max Range: 0.8020. Min Range: -0.8020

Max Act: 0.7191. Min Act: -0.0000

Data Index: 583358 (The Pile)

Max Activating Token Index: 487

Text #12

Max Range: 0.8020. Min Range: -0.8020

Max Act: 0.7521. Min Act: -0.0000

Data Index: 1387456 (The Pile)

Max Activating Token Index: 457

Text #13

Max Range: 0.8020. Min Range: -0.8020

Max Act: 0.6747. Min Act: -0.0000

Data Index: 1318867 (The Pile)

Max Activating Token Index: 965

Text #14

Max Range: 0.8020. Min Range: -0.8020

Max Act: 0.7517. Min Act: -0.0000

Data Index: 1188948 (The Pile)

Max Activating Token Index: 562

Text #15

Max Range: 0.8020. Min Range: -0.8020

Max Act: 0.7213. Min Act: -0.0000

Data Index: 1212353 (The Pile)

Max Activating Token Index: 255

Text #16

Max Range: 0.8020. Min Range: -0.8020

Max Act: 0.7010. Min Act: -0.0000

Data Index: 1229929 (The Pile)

Max Activating Token Index: 882

Text #17

Max Range: 0.8020. Min Range: -0.8020

Max Act: 0.7145. Min Act: -0.0000

Data Index: 271200 (The Pile)

Max Activating Token Index: 150

Text #18

Max Range: 0.8020. Min Range: -0.8020

Max Act: 0.7069. Min Act: -0.0000

Data Index: 409299 (The Pile)

Max Activating Token Index: 426

Text #19

Max Range: 0.8020. Min Range: -0.8020

Max Act: 0.7528. Min Act: -0.0000

Data Index: 1565666 (The Pile)

Max Activating Token Index: 881