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

Dataset: The Pile

Neuron 5102 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: 1.4798. Min Range: -1.4798

Max Act: 1.4798. Min Act: -0.0000

Data Index: 924429 (The Pile)

Max Activating Token Index: 410

Text #1

Max Range: 1.4798. Min Range: -1.4798

Max Act: 1.3544. Min Act: -0.0000

Data Index: 822399 (The Pile)

Max Activating Token Index: 411

Text #2

Max Range: 1.4798. Min Range: -1.4798

Max Act: 1.2598. Min Act: -0.0000

Data Index: 689490 (The Pile)

Max Activating Token Index: 345

Text #3

Max Range: 1.4798. Min Range: -1.4798

Max Act: 1.0310. Min Act: -0.0000

Data Index: 1873364 (The Pile)

Max Activating Token Index: 486

Text #4

Max Range: 1.4798. Min Range: -1.4798

Max Act: 1.0852. Min Act: -0.0000

Data Index: 477047 (The Pile)

Max Activating Token Index: 685

Text #5

Max Range: 1.4798. Min Range: -1.4798

Max Act: 1.1069. Min Act: -0.0000

Data Index: 1521294 (The Pile)

Max Activating Token Index: 564

Text #6

Max Range: 1.4798. Min Range: -1.4798

Max Act: 1.1263. Min Act: -0.0000

Data Index: 327870 (The Pile)

Max Activating Token Index: 911

Text #7

Max Range: 1.4798. Min Range: -1.4798

Max Act: 1.0741. Min Act: -0.0000

Data Index: 809937 (The Pile)

Max Activating Token Index: 367

Text #8

Max Range: 1.4798. Min Range: -1.4798

Max Act: 1.0279. Min Act: -0.0000

Data Index: 420800 (The Pile)

Max Activating Token Index: 524

Text #9

Max Range: 1.4798. Min Range: -1.4798

Max Act: 0.9991. Min Act: -0.0000

Data Index: 1752663 (The Pile)

Max Activating Token Index: 759

Text #10

Max Range: 1.4798. Min Range: -1.4798

Max Act: 1.0278. Min Act: -0.0000

Data Index: 471536 (The Pile)

Max Activating Token Index: 274

Text #11

Max Range: 1.4798. Min Range: -1.4798

Max Act: 0.9637. Min Act: -0.0000

Data Index: 1842509 (The Pile)

Max Activating Token Index: 60

Text #12

Max Range: 1.4798. Min Range: -1.4798

Max Act: 1.0073. Min Act: -0.0000

Data Index: 1135126 (The Pile)

Max Activating Token Index: 138

Text #13

Max Range: 1.4798. Min Range: -1.4798

Max Act: 0.8897. Min Act: -0.0000

Data Index: 1389859 (The Pile)

Max Activating Token Index: 970

Text #14

Max Range: 1.4798. Min Range: -1.4798

Max Act: 0.9962. Min Act: -0.0000

Data Index: 1532089 (The Pile)

Max Activating Token Index: 725

Text #15

Max Range: 1.4798. Min Range: -1.4798

Max Act: 0.8947. Min Act: -0.0000

Data Index: 265339 (The Pile)

Max Activating Token Index: 292

Text #16

Max Range: 1.4798. Min Range: -1.4798

Max Act: 0.9386. Min Act: -0.0000

Data Index: 754297 (The Pile)

Max Activating Token Index: 677

Text #17

Max Range: 1.4798. Min Range: -1.4798

Max Act: 0.9916. Min Act: -0.0000

Data Index: 1378598 (The Pile)

Max Activating Token Index: 533

Text #18

Max Range: 1.4798. Min Range: -1.4798

Max Act: 0.8956. Min Act: -0.0000

Data Index: 1595594 (The Pile)

Max Activating Token Index: 714

Text #19

Max Range: 1.4798. Min Range: -1.4798

Max Act: 0.9136. Min Act: -0.0000

Data Index: 13387 (The Pile)

Max Activating Token Index: 857