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

Dataset: The Pile

Neuron 629 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: 1.2624. Min Range: -1.2624

Max Act: 1.2624. Min Act: -0.0000

Data Index: 781594 (The Pile)

Max Activating Token Index: 428

Text #1

Max Range: 1.2624. Min Range: -1.2624

Max Act: 1.0060. Min Act: -0.0000

Data Index: 208188 (The Pile)

Max Activating Token Index: 1000

Text #2

Max Range: 1.2624. Min Range: -1.2624

Max Act: 0.9592. Min Act: -0.0000

Data Index: 547684 (The Pile)

Max Activating Token Index: 76

Text #3

Max Range: 1.2624. Min Range: -1.2624

Max Act: 0.9260. Min Act: -0.0000

Data Index: 594675 (The Pile)

Max Activating Token Index: 399

Text #4

Max Range: 1.2624. Min Range: -1.2624

Max Act: 0.9239. Min Act: -0.0000

Data Index: 1339466 (The Pile)

Max Activating Token Index: 445

Text #5

Max Range: 1.2624. Min Range: -1.2624

Max Act: 0.8932. Min Act: -0.0000

Data Index: 761485 (The Pile)

Max Activating Token Index: 357

Text #6

Max Range: 1.2624. Min Range: -1.2624

Max Act: 0.9134. Min Act: -0.0000

Data Index: 674323 (The Pile)

Max Activating Token Index: 202

Text #7

Max Range: 1.2624. Min Range: -1.2624

Max Act: 0.8732. Min Act: -0.0000

Data Index: 1467525 (The Pile)

Max Activating Token Index: 454

Text #8

Max Range: 1.2624. Min Range: -1.2624

Max Act: 0.8227. Min Act: -0.0000

Data Index: 1715462 (The Pile)

Max Activating Token Index: 904

Text #9

Max Range: 1.2624. Min Range: -1.2624

Max Act: 0.8856. Min Act: -0.0000

Data Index: 991186 (The Pile)

Max Activating Token Index: 52

Text #10

Max Range: 1.2624. Min Range: -1.2624

Max Act: 0.8951. Min Act: -0.0000

Data Index: 519122 (The Pile)

Max Activating Token Index: 513

Text #11

Max Range: 1.2624. Min Range: -1.2624

Max Act: 0.8188. Min Act: -0.0000

Data Index: 1087529 (The Pile)

Max Activating Token Index: 1023

Text #12

Max Range: 1.2624. Min Range: -1.2624

Max Act: 0.7912. Min Act: -0.0000

Data Index: 1205235 (The Pile)

Max Activating Token Index: 21

Text #13

Max Range: 1.2624. Min Range: -1.2624

Max Act: 0.7515. Min Act: -0.0000

Data Index: 699316 (The Pile)

Max Activating Token Index: 396

Text #14

Max Range: 1.2624. Min Range: -1.2624

Max Act: 0.7084. Min Act: -0.0000

Data Index: 1965390 (The Pile)

Max Activating Token Index: 993

Text #15

Max Range: 1.2624. Min Range: -1.2624

Max Act: 0.7614. Min Act: -0.0000

Data Index: 268818 (The Pile)

Max Activating Token Index: 344

Text #16

Max Range: 1.2624. Min Range: -1.2624

Max Act: 0.7400. Min Act: -0.0000

Data Index: 358404 (The Pile)

Max Activating Token Index: 314

Text #17

Max Range: 1.2624. Min Range: -1.2624

Max Act: 0.7593. Min Act: -0.0000

Data Index: 251838 (The Pile)

Max Activating Token Index: 443

Text #18

Max Range: 1.2624. Min Range: -1.2624

Max Act: 0.7259. Min Act: -0.0000

Data Index: 1913066 (The Pile)

Max Activating Token Index: 28

Text #19

Max Range: 1.2624. Min Range: -1.2624

Max Act: 0.7191. Min Act: -0.0000

Data Index: 1454718 (The Pile)

Max Activating Token Index: 458