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

Dataset: The Pile

Neuron 764 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: 1.9654. Min Range: -1.9654

Max Act: 1.9654. Min Act: -0.0000

Data Index: 1915286 (The Pile)

Max Activating Token Index: 567

Text #1

Max Range: 1.9654. Min Range: -1.9654

Max Act: 1.8869. Min Act: 0.0000

Data Index: 1098761 (The Pile)

Max Activating Token Index: 321

Text #2

Max Range: 1.9654. Min Range: -1.9654

Max Act: 1.8044. Min Act: -0.0000

Data Index: 291017 (The Pile)

Max Activating Token Index: 663

Text #3

Max Range: 1.9654. Min Range: -1.9654

Max Act: 1.8463. Min Act: -0.0000

Data Index: 1451928 (The Pile)

Max Activating Token Index: 89

Text #4

Max Range: 1.9654. Min Range: -1.9654

Max Act: 1.8399. Min Act: -0.0000

Data Index: 1626678 (The Pile)

Max Activating Token Index: 262

Text #5

Max Range: 1.9654. Min Range: -1.9654

Max Act: 1.9141. Min Act: -0.0000

Data Index: 1807454 (The Pile)

Max Activating Token Index: 160

Text #6

Max Range: 1.9654. Min Range: -1.9654

Max Act: 1.7938. Min Act: -0.0000

Data Index: 1230219 (The Pile)

Max Activating Token Index: 297

Text #7

Max Range: 1.9654. Min Range: -1.9654

Max Act: 1.7733. Min Act: -0.0000

Data Index: 420168 (The Pile)

Max Activating Token Index: 1012

Text #8

Max Range: 1.9654. Min Range: -1.9654

Max Act: 1.8380. Min Act: -0.0000

Data Index: 505633 (The Pile)

Max Activating Token Index: 76

Text #9

Max Range: 1.9654. Min Range: -1.9654

Max Act: 1.7186. Min Act: -0.0000

Data Index: 1624044 (The Pile)

Max Activating Token Index: 271

Text #10

Max Range: 1.9654. Min Range: -1.9654

Max Act: 1.7675. Min Act: -0.0000

Data Index: 514481 (The Pile)

Max Activating Token Index: 333

Text #11

Max Range: 1.9654. Min Range: -1.9654

Max Act: 1.6621. Min Act: -0.0000

Data Index: 363350 (The Pile)

Max Activating Token Index: 59

Text #12

Max Range: 1.9654. Min Range: -1.9654

Max Act: 1.7411. Min Act: -0.0000

Data Index: 439165 (The Pile)

Max Activating Token Index: 615

Text #13

Max Range: 1.9654. Min Range: -1.9654

Max Act: 1.7408. Min Act: -0.0000

Data Index: 1564317 (The Pile)

Max Activating Token Index: 634

Text #14

Max Range: 1.9654. Min Range: -1.9654

Max Act: 1.6238. Min Act: -0.0000

Data Index: 762138 (The Pile)

Max Activating Token Index: 392

Text #15

Max Range: 1.9654. Min Range: -1.9654

Max Act: 1.5980. Min Act: -0.0000

Data Index: 1838332 (The Pile)

Max Activating Token Index: 709

Text #16

Max Range: 1.9654. Min Range: -1.9654

Max Act: 1.5891. Min Act: -0.0000

Data Index: 1429532 (The Pile)

Max Activating Token Index: 352

Text #17

Max Range: 1.9654. Min Range: -1.9654

Max Act: 1.5712. Min Act: -0.0000

Data Index: 944981 (The Pile)

Max Activating Token Index: 59

Text #18

Max Range: 1.9654. Min Range: -1.9654

Max Act: 1.6691. Min Act: -0.0000

Data Index: 1864453 (The Pile)

Max Activating Token Index: 729

Text #19

Max Range: 1.9654. Min Range: -1.9654

Max Act: 1.5788. Min Act: -0.0000

Data Index: 1935415 (The Pile)

Max Activating Token Index: 42