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

Dataset: The Pile

Neuron 726 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.9974. Min Range: -0.9974

Max Act: 0.9974. Min Act: -0.0000

Data Index: 1540654 (The Pile)

Max Activating Token Index: 962

Text #1

Max Range: 0.9974. Min Range: -0.9974

Max Act: 0.9260. Min Act: -0.0000

Data Index: 98333 (The Pile)

Max Activating Token Index: 301

Text #2

Max Range: 0.9974. Min Range: -0.9974

Max Act: 0.9456. Min Act: -0.0000

Data Index: 1159383 (The Pile)

Max Activating Token Index: 227

Text #3

Max Range: 0.9974. Min Range: -0.9974

Max Act: 0.9120. Min Act: -0.0000

Data Index: 1313833 (The Pile)

Max Activating Token Index: 193

Text #4

Max Range: 0.9974. Min Range: -0.9974

Max Act: 0.9224. Min Act: -0.0000

Data Index: 376258 (The Pile)

Max Activating Token Index: 85

Text #5

Max Range: 0.9974. Min Range: -0.9974

Max Act: 0.9195. Min Act: -0.0000

Data Index: 144525 (The Pile)

Max Activating Token Index: 180

Text #6

Max Range: 0.9974. Min Range: -0.9974

Max Act: 0.8012. Min Act: -0.0000

Data Index: 456981 (The Pile)

Max Activating Token Index: 342

Text #7

Max Range: 0.9974. Min Range: -0.9974

Max Act: 0.8379. Min Act: -0.0000

Data Index: 1529582 (The Pile)

Max Activating Token Index: 96

Text #8

Max Range: 0.9974. Min Range: -0.9974

Max Act: 0.8670. Min Act: -0.0000

Data Index: 245828 (The Pile)

Max Activating Token Index: 304

Text #9

Max Range: 0.9974. Min Range: -0.9974

Max Act: 0.8317. Min Act: -0.0000

Data Index: 791460 (The Pile)

Max Activating Token Index: 301

Text #10

Max Range: 0.9974. Min Range: -0.9974

Max Act: 0.8302. Min Act: -0.0000

Data Index: 500107 (The Pile)

Max Activating Token Index: 493

Text #11

Max Range: 0.9974. Min Range: -0.9974

Max Act: 0.8140. Min Act: -0.0000

Data Index: 1422636 (The Pile)

Max Activating Token Index: 446

Text #12

Max Range: 0.9974. Min Range: -0.9974

Max Act: 0.8064. Min Act: -0.0000

Data Index: 1165238 (The Pile)

Max Activating Token Index: 830

Text #13

Max Range: 0.9974. Min Range: -0.9974

Max Act: 0.8039. Min Act: -0.0000

Data Index: 795746 (The Pile)

Max Activating Token Index: 152

Text #14

Max Range: 0.9974. Min Range: -0.9974

Max Act: 0.7715. Min Act: -0.0000

Data Index: 1434250 (The Pile)

Max Activating Token Index: 292

Text #15

Max Range: 0.9974. Min Range: -0.9974

Max Act: 0.8088. Min Act: -0.0000

Data Index: 1917086 (The Pile)

Max Activating Token Index: 682

Text #16

Max Range: 0.9974. Min Range: -0.9974

Max Act: 0.7425. Min Act: -0.0000

Data Index: 754847 (The Pile)

Max Activating Token Index: 77

Text #17

Max Range: 0.9974. Min Range: -0.9974

Max Act: 0.7819. Min Act: -0.0000

Data Index: 469044 (The Pile)

Max Activating Token Index: 580

Text #18

Max Range: 0.9974. Min Range: -0.9974

Max Act: 0.7805. Min Act: -0.0000

Data Index: 329309 (The Pile)

Max Activating Token Index: 802

Text #19

Max Range: 0.9974. Min Range: -0.9974

Max Act: 0.7814. Min Act: -0.0000

Data Index: 449589 (The Pile)

Max Activating Token Index: 259