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

Dataset: The Pile

Neuron 4280 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: 0.1275. Min Range: -0.1275

Max Act: 0.1275. Min Act: -0.0000

Data Index: 1883463 (The Pile)

Max Activating Token Index: 882

Text #1

Max Range: 0.1275. Min Range: -0.1275

Max Act: 0.1228. Min Act: -0.0000

Data Index: 164433 (The Pile)

Max Activating Token Index: 189

Text #2

Max Range: 0.1275. Min Range: -0.1275

Max Act: 0.0842. Min Act: -0.0000

Data Index: 1767177 (The Pile)

Max Activating Token Index: 290

Text #3

Max Range: 0.1275. Min Range: -0.1275

Max Act: 0.0985. Min Act: -0.0000

Data Index: 1290499 (The Pile)

Max Activating Token Index: 852

Text #4

Max Range: 0.1275. Min Range: -0.1275

Max Act: 0.0948. Min Act: -0.0000

Data Index: 1185149 (The Pile)

Max Activating Token Index: 67

Text #5

Max Range: 0.1275. Min Range: -0.1275

Max Act: 0.0813. Min Act: 0.0000

Data Index: 1262269 (The Pile)

Max Activating Token Index: 132

Text #6

Max Range: 0.1275. Min Range: -0.1275

Max Act: 0.0860. Min Act: -0.0000

Data Index: 654775 (The Pile)

Max Activating Token Index: 355

Text #7

Max Range: 0.1275. Min Range: -0.1275

Max Act: 0.0932. Min Act: -0.0000

Data Index: 1698346 (The Pile)

Max Activating Token Index: 580

Text #8

Max Range: 0.1275. Min Range: -0.1275

Max Act: 0.0844. Min Act: 0.0000

Data Index: 114856 (The Pile)

Max Activating Token Index: 582

Text #9

Max Range: 0.1275. Min Range: -0.1275

Max Act: 0.0718. Min Act: -0.0000

Data Index: 887530 (The Pile)

Max Activating Token Index: 177

Text #10

Max Range: 0.1275. Min Range: -0.1275

Max Act: 0.0771. Min Act: -0.0000

Data Index: 1579533 (The Pile)

Max Activating Token Index: 803

Text #11

Max Range: 0.1275. Min Range: -0.1275

Max Act: 0.0851. Min Act: -0.0000

Data Index: 1840358 (The Pile)

Max Activating Token Index: 543

Text #12

Max Range: 0.1275. Min Range: -0.1275

Max Act: 0.0780. Min Act: -0.0000

Data Index: 503004 (The Pile)

Max Activating Token Index: 651

Text #13

Max Range: 0.1275. Min Range: -0.1275

Max Act: 0.0872. Min Act: -0.0000

Data Index: 430658 (The Pile)

Max Activating Token Index: 169

Text #14

Max Range: 0.1275. Min Range: -0.1275

Max Act: 0.0753. Min Act: -0.0000

Data Index: 322355 (The Pile)

Max Activating Token Index: 506

Text #15

Max Range: 0.1275. Min Range: -0.1275

Max Act: 0.0804. Min Act: -0.0000

Data Index: 1583005 (The Pile)

Max Activating Token Index: 6

Text #16

Max Range: 0.1275. Min Range: -0.1275

Max Act: 0.0770. Min Act: 0.0000

Data Index: 236399 (The Pile)

Max Activating Token Index: 625

Text #17

Max Range: 0.1275. Min Range: -0.1275

Max Act: 0.0747. Min Act: -0.0000

Data Index: 192720 (The Pile)

Max Activating Token Index: 503

Text #18

Max Range: 0.1275. Min Range: -0.1275

Max Act: 0.0778. Min Act: -0.0000

Data Index: 247720 (The Pile)

Max Activating Token Index: 770

Text #19

Max Range: 0.1275. Min Range: -0.1275

Max Act: 0.0753. Min Act: -0.0000

Data Index: 661738 (The Pile)

Max Activating Token Index: 506