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

Dataset: The Pile

Neuron 2687 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: 1.6726. Min Range: -1.6726

Max Act: 1.6726. Min Act: -0.0000

Data Index: 1266529 (The Pile)

Max Activating Token Index: 397

Text #1

Max Range: 1.6726. Min Range: -1.6726

Max Act: 1.1532. Min Act: -0.0000

Data Index: 1447612 (The Pile)

Max Activating Token Index: 328

Text #2

Max Range: 1.6726. Min Range: -1.6726

Max Act: 1.1179. Min Act: -0.0000

Data Index: 1396615 (The Pile)

Max Activating Token Index: 711

Text #3

Max Range: 1.6726. Min Range: -1.6726

Max Act: 1.1603. Min Act: -0.0000

Data Index: 1802702 (The Pile)

Max Activating Token Index: 365

Text #4

Max Range: 1.6726. Min Range: -1.6726

Max Act: 1.0799. Min Act: -0.0000

Data Index: 411892 (The Pile)

Max Activating Token Index: 619

Text #5

Max Range: 1.6726. Min Range: -1.6726

Max Act: 1.0471. Min Act: -0.0000

Data Index: 299263 (The Pile)

Max Activating Token Index: 53

Text #6

Max Range: 1.6726. Min Range: -1.6726

Max Act: 1.0197. Min Act: -0.0000

Data Index: 720543 (The Pile)

Max Activating Token Index: 54

Text #7

Max Range: 1.6726. Min Range: -1.6726

Max Act: 1.0490. Min Act: -0.0000

Data Index: 1218538 (The Pile)

Max Activating Token Index: 138

Text #8

Max Range: 1.6726. Min Range: -1.6726

Max Act: 0.9726. Min Act: 0.0000

Data Index: 1894381 (The Pile)

Max Activating Token Index: 412

Text #9

Max Range: 1.6726. Min Range: -1.6726

Max Act: 0.9588. Min Act: -0.0000

Data Index: 1959058 (The Pile)

Max Activating Token Index: 222

Text #10

Max Range: 1.6726. Min Range: -1.6726

Max Act: 1.0268. Min Act: -0.0000

Data Index: 127256 (The Pile)

Max Activating Token Index: 644

Text #11

Max Range: 1.6726. Min Range: -1.6726

Max Act: 0.9671. Min Act: 0.0000

Data Index: 1337318 (The Pile)

Max Activating Token Index: 388

Text #12

Max Range: 1.6726. Min Range: -1.6726

Max Act: 0.9590. Min Act: -0.0000

Data Index: 1654417 (The Pile)

Max Activating Token Index: 641

Text #13

Max Range: 1.6726. Min Range: -1.6726

Max Act: 0.9435. Min Act: -0.0000

Data Index: 1107004 (The Pile)

Max Activating Token Index: 527

Text #14

Max Range: 1.6726. Min Range: -1.6726

Max Act: 0.8799. Min Act: -0.0000

Data Index: 1146284 (The Pile)

Max Activating Token Index: 736

Text #15

Max Range: 1.6726. Min Range: -1.6726

Max Act: 0.9143. Min Act: 0.0000

Data Index: 1403511 (The Pile)

Max Activating Token Index: 588

Text #16

Max Range: 1.6726. Min Range: -1.6726

Max Act: 0.8525. Min Act: 0.0000

Data Index: 669090 (The Pile)

Max Activating Token Index: 867

Text #17

Max Range: 1.6726. Min Range: -1.6726

Max Act: 0.9005. Min Act: 0.0000

Data Index: 1376509 (The Pile)

Max Activating Token Index: 727

Text #18

Max Range: 1.6726. Min Range: -1.6726

Max Act: 0.8942. Min Act: -0.0000

Data Index: 595309 (The Pile)

Max Activating Token Index: 519

Text #19

Max Range: 1.6726. Min Range: -1.6726

Max Act: 0.9380. Min Act: -0.0000

Data Index: 869337 (The Pile)

Max Activating Token Index: 69