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

Dataset: The Pile

Neuron 3614 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6358. Min Range: -0.6358

Max Act: 0.6358. Min Act: -0.0000

Data Index: 343136 (The Pile)

Max Activating Token Index: 45

Text #1

Max Range: 0.6358. Min Range: -0.6358

Max Act: 0.5915. Min Act: -0.0000

Data Index: 344198 (The Pile)

Max Activating Token Index: 1008

Text #2

Max Range: 0.6358. Min Range: -0.6358

Max Act: 0.5795. Min Act: 0.0000

Data Index: 1561795 (The Pile)

Max Activating Token Index: 798

Text #3

Max Range: 0.6358. Min Range: -0.6358

Max Act: 0.5600. Min Act: -0.0000

Data Index: 1721485 (The Pile)

Max Activating Token Index: 596

Text #4

Max Range: 0.6358. Min Range: -0.6358

Max Act: 0.5622. Min Act: -0.0000

Data Index: 523910 (The Pile)

Max Activating Token Index: 400

Text #5

Max Range: 0.6358. Min Range: -0.6358

Max Act: 0.5776. Min Act: -0.0000

Data Index: 1807035 (The Pile)

Max Activating Token Index: 542

Text #6

Max Range: 0.6358. Min Range: -0.6358

Max Act: 0.5921. Min Act: -0.0000

Data Index: 1543419 (The Pile)

Max Activating Token Index: 140

Text #7

Max Range: 0.6358. Min Range: -0.6358

Max Act: 0.5239. Min Act: -0.0000

Data Index: 785347 (The Pile)

Max Activating Token Index: 56

Text #8

Max Range: 0.6358. Min Range: -0.6358

Max Act: 0.5983. Min Act: -0.0000

Data Index: 136283 (The Pile)

Max Activating Token Index: 176

Text #9

Max Range: 0.6358. Min Range: -0.6358

Max Act: 0.5428. Min Act: -0.0000

Data Index: 1514355 (The Pile)

Max Activating Token Index: 354

Text #10

Max Range: 0.6358. Min Range: -0.6358

Max Act: 0.5210. Min Act: -0.0000

Data Index: 367780 (The Pile)

Max Activating Token Index: 379

Text #11

Max Range: 0.6358. Min Range: -0.6358

Max Act: 0.5167. Min Act: -0.0000

Data Index: 1627007 (The Pile)

Max Activating Token Index: 794

Text #12

Max Range: 0.6358. Min Range: -0.6358

Max Act: 0.5123. Min Act: -0.0000

Data Index: 1481942 (The Pile)

Max Activating Token Index: 744

Text #13

Max Range: 0.6358. Min Range: -0.6358

Max Act: 0.5018. Min Act: -0.0000

Data Index: 1582328 (The Pile)

Max Activating Token Index: 427

Text #14

Max Range: 0.6358. Min Range: -0.6358

Max Act: 0.5033. Min Act: -0.0000

Data Index: 840841 (The Pile)

Max Activating Token Index: 544

Text #15

Max Range: 0.6358. Min Range: -0.6358

Max Act: 0.5175. Min Act: -0.0000

Data Index: 1066672 (The Pile)

Max Activating Token Index: 242

Text #16

Max Range: 0.6358. Min Range: -0.6358

Max Act: 0.5033. Min Act: -0.0000

Data Index: 761071 (The Pile)

Max Activating Token Index: 987

Text #17

Max Range: 0.6358. Min Range: -0.6358

Max Act: 0.4785. Min Act: -0.0000

Data Index: 788890 (The Pile)

Max Activating Token Index: 796

Text #18

Max Range: 0.6358. Min Range: -0.6358

Max Act: 0.5073. Min Act: -0.0000

Data Index: 368965 (The Pile)

Max Activating Token Index: 244

Text #19

Max Range: 0.6358. Min Range: -0.6358

Max Act: 0.4899. Min Act: -0.0000

Data Index: 1327264 (The Pile)

Max Activating Token Index: 797