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

Dataset: The Pile

Neuron 2655 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: 0.6581. Min Range: -0.6581

Max Act: 0.6218. Min Act: 0.0000

Data Index: 1321894 (The Pile)

Max Activating Token Index: 495

Text #1

Max Range: 0.6581. Min Range: -0.6581

Max Act: 0.6577. Min Act: -0.0000

Data Index: 778953 (The Pile)

Max Activating Token Index: 810

Text #2

Max Range: 0.6581. Min Range: -0.6581

Max Act: 0.6499. Min Act: -0.0000

Data Index: 1042229 (The Pile)

Max Activating Token Index: 299

Text #3

Max Range: 0.6581. Min Range: -0.6581

Max Act: 0.6581. Min Act: -0.0000

Data Index: 242044 (The Pile)

Max Activating Token Index: 805

Text #4

Max Range: 0.6581. Min Range: -0.6581

Max Act: 0.6075. Min Act: -0.0000

Data Index: 1596968 (The Pile)

Max Activating Token Index: 577

Text #5

Max Range: 0.6581. Min Range: -0.6581

Max Act: 0.6277. Min Act: -0.0000

Data Index: 290591 (The Pile)

Max Activating Token Index: 224

Text #6

Max Range: 0.6581. Min Range: -0.6581

Max Act: 0.6305. Min Act: -0.0000

Data Index: 670244 (The Pile)

Max Activating Token Index: 497

Text #7

Max Range: 0.6581. Min Range: -0.6581

Max Act: 0.6256. Min Act: -0.0000

Data Index: 1644283 (The Pile)

Max Activating Token Index: 584

Text #8

Max Range: 0.6581. Min Range: -0.6581

Max Act: 0.5970. Min Act: -0.0000

Data Index: 1070140 (The Pile)

Max Activating Token Index: 587

Text #9

Max Range: 0.6581. Min Range: -0.6581

Max Act: 0.6031. Min Act: -0.0000

Data Index: 880689 (The Pile)

Max Activating Token Index: 215

Text #10

Max Range: 0.6581. Min Range: -0.6581

Max Act: 0.6433. Min Act: -0.0000

Data Index: 703323 (The Pile)

Max Activating Token Index: 573

Text #11

Max Range: 0.6581. Min Range: -0.6581

Max Act: 0.5984. Min Act: 0.0000

Data Index: 533186 (The Pile)

Max Activating Token Index: 293

Text #12

Max Range: 0.6581. Min Range: -0.6581

Max Act: 0.5974. Min Act: -0.0000

Data Index: 1988895 (The Pile)

Max Activating Token Index: 340

Text #13

Max Range: 0.6581. Min Range: -0.6581

Max Act: 0.6083. Min Act: -0.0000

Data Index: 1329892 (The Pile)

Max Activating Token Index: 737

Text #14

Max Range: 0.6581. Min Range: -0.6581

Max Act: 0.5861. Min Act: -0.0000

Data Index: 1012138 (The Pile)

Max Activating Token Index: 978

Text #15

Max Range: 0.6581. Min Range: -0.6581

Max Act: 0.6278. Min Act: -0.0000

Data Index: 468704 (The Pile)

Max Activating Token Index: 459

Text #16

Max Range: 0.6581. Min Range: -0.6581

Max Act: 0.5672. Min Act: -0.0000

Data Index: 625 (The Pile)

Max Activating Token Index: 1017

Text #17

Max Range: 0.6581. Min Range: -0.6581

Max Act: 0.6232. Min Act: -0.0000

Data Index: 1813119 (The Pile)

Max Activating Token Index: 266

Text #18

Max Range: 0.6581. Min Range: -0.6581

Max Act: 0.6224. Min Act: -0.0000

Data Index: 1618880 (The Pile)

Max Activating Token Index: 542

Text #19

Max Range: 0.6581. Min Range: -0.6581

Max Act: 0.6089. Min Act: -0.0000

Data Index: 690716 (The Pile)

Max Activating Token Index: 993