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

Dataset: The Pile

Neuron 3039 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.7080. Min Range: -4.7080

Max Act: 4.7080. Min Act: -0.0000

Data Index: 1481441 (The Pile)

Max Activating Token Index: 743

Text #1

Max Range: 4.7080. Min Range: -4.7080

Max Act: 3.7614. Min Act: -0.0000

Data Index: 1696937 (The Pile)

Max Activating Token Index: 315

Text #2

Max Range: 4.7080. Min Range: -4.7080

Max Act: 3.7839. Min Act: -0.0000

Data Index: 1745216 (The Pile)

Max Activating Token Index: 286

Text #3

Max Range: 4.7080. Min Range: -4.7080

Max Act: 3.4721. Min Act: -0.0000

Data Index: 1241627 (The Pile)

Max Activating Token Index: 416

Text #4

Max Range: 4.7080. Min Range: -4.7080

Max Act: 3.6528. Min Act: -0.0000

Data Index: 914833 (The Pile)

Max Activating Token Index: 697

Text #5

Max Range: 4.7080. Min Range: -4.7080

Max Act: 3.4867. Min Act: -0.0000

Data Index: 1387795 (The Pile)

Max Activating Token Index: 713

Text #6

Max Range: 4.7080. Min Range: -4.7080

Max Act: 3.6202. Min Act: -0.0000

Data Index: 184971 (The Pile)

Max Activating Token Index: 947

Text #7

Max Range: 4.7080. Min Range: -4.7080

Max Act: 3.3765. Min Act: -0.0000

Data Index: 990804 (The Pile)

Max Activating Token Index: 256

Text #8

Max Range: 4.7080. Min Range: -4.7080

Max Act: 3.5238. Min Act: -0.0000

Data Index: 1418874 (The Pile)

Max Activating Token Index: 388

Text #9

Max Range: 4.7080. Min Range: -4.7080

Max Act: 3.3520. Min Act: -0.0000

Data Index: 3458 (The Pile)

Max Activating Token Index: 693

Text #10

Max Range: 4.7080. Min Range: -4.7080

Max Act: 3.2714. Min Act: -0.0000

Data Index: 1674954 (The Pile)

Max Activating Token Index: 558

Text #11

Max Range: 4.7080. Min Range: -4.7080

Max Act: 3.2543. Min Act: -0.0000

Data Index: 204881 (The Pile)

Max Activating Token Index: 242

Text #12

Max Range: 4.7080. Min Range: -4.7080

Max Act: 3.0856. Min Act: -0.0000

Data Index: 1178379 (The Pile)

Max Activating Token Index: 568

Text #13

Max Range: 4.7080. Min Range: -4.7080

Max Act: 3.0699. Min Act: -0.0000

Data Index: 952797 (The Pile)

Max Activating Token Index: 532

Text #14

Max Range: 4.7080. Min Range: -4.7080

Max Act: 3.3793. Min Act: -0.0000

Data Index: 475552 (The Pile)

Max Activating Token Index: 607

Text #15

Max Range: 4.7080. Min Range: -4.7080

Max Act: 3.1909. Min Act: -0.0000

Data Index: 1892130 (The Pile)

Max Activating Token Index: 785

Text #16

Max Range: 4.7080. Min Range: -4.7080

Max Act: 3.3818. Min Act: -0.0000

Data Index: 1935355 (The Pile)

Max Activating Token Index: 187

Text #17

Max Range: 4.7080. Min Range: -4.7080

Max Act: 3.3656. Min Act: -0.0000

Data Index: 1305848 (The Pile)

Max Activating Token Index: 295

Text #18

Max Range: 4.7080. Min Range: -4.7080

Max Act: 3.3651. Min Act: -0.0000

Data Index: 952464 (The Pile)

Max Activating Token Index: 271

Text #19

Max Range: 4.7080. Min Range: -4.7080

Max Act: 3.1850. Min Act: -0.0000

Data Index: 1935704 (The Pile)

Max Activating Token Index: 423