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

Dataset: The Pile

Neuron 1561 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.9225. Min Range: -5.9225

Max Act: 5.9225. Min Act: -0.0000

Data Index: 922113 (The Pile)

Max Activating Token Index: 333

Text #1

Max Range: 5.9225. Min Range: -5.9225

Max Act: 5.6393. Min Act: -0.0000

Data Index: 439553 (The Pile)

Max Activating Token Index: 966

Text #2

Max Range: 5.9225. Min Range: -5.9225

Max Act: 5.5523. Min Act: -0.0000

Data Index: 625861 (The Pile)

Max Activating Token Index: 558

Text #3

Max Range: 5.9225. Min Range: -5.9225

Max Act: 5.2717. Min Act: -0.0000

Data Index: 960996 (The Pile)

Max Activating Token Index: 440

Text #4

Max Range: 5.9225. Min Range: -5.9225

Max Act: 5.0141. Min Act: -0.0000

Data Index: 910462 (The Pile)

Max Activating Token Index: 639

Text #5

Max Range: 5.9225. Min Range: -5.9225

Max Act: 5.5706. Min Act: -0.0000

Data Index: 48882 (The Pile)

Max Activating Token Index: 502

Text #6

Max Range: 5.9225. Min Range: -5.9225

Max Act: 5.1620. Min Act: -0.0000

Data Index: 1761799 (The Pile)

Max Activating Token Index: 450

Text #7

Max Range: 5.9225. Min Range: -5.9225

Max Act: 5.3443. Min Act: -0.0000

Data Index: 1154911 (The Pile)

Max Activating Token Index: 519

Text #8

Max Range: 5.9225. Min Range: -5.9225

Max Act: 5.1110. Min Act: -0.0000

Data Index: 229133 (The Pile)

Max Activating Token Index: 763

Text #9

Max Range: 5.9225. Min Range: -5.9225

Max Act: 5.2813. Min Act: -0.0000

Data Index: 1370409 (The Pile)

Max Activating Token Index: 889

Text #10

Max Range: 5.9225. Min Range: -5.9225

Max Act: 5.2457. Min Act: -0.0000

Data Index: 1908963 (The Pile)

Max Activating Token Index: 940

Text #11

Max Range: 5.9225. Min Range: -5.9225

Max Act: 5.2043. Min Act: -0.0000

Data Index: 984447 (The Pile)

Max Activating Token Index: 545

Text #12

Max Range: 5.9225. Min Range: -5.9225

Max Act: 5.1664. Min Act: -0.0000

Data Index: 303769 (The Pile)

Max Activating Token Index: 336

Text #13

Max Range: 5.9225. Min Range: -5.9225

Max Act: 4.9911. Min Act: -0.0000

Data Index: 1183041 (The Pile)

Max Activating Token Index: 876

Text #14

Max Range: 5.9225. Min Range: -5.9225

Max Act: 5.1002. Min Act: -0.0000

Data Index: 1037410 (The Pile)

Max Activating Token Index: 706

Text #15

Max Range: 5.9225. Min Range: -5.9225

Max Act: 5.2579. Min Act: -0.0000

Data Index: 1224341 (The Pile)

Max Activating Token Index: 592

Text #16

Max Range: 5.9225. Min Range: -5.9225

Max Act: 5.0588. Min Act: -0.0000

Data Index: 1009638 (The Pile)

Max Activating Token Index: 624

Text #17

Max Range: 5.9225. Min Range: -5.9225

Max Act: 5.2460. Min Act: -0.0000

Data Index: 1595148 (The Pile)

Max Activating Token Index: 996

Text #18

Max Range: 5.9225. Min Range: -5.9225

Max Act: 5.0322. Min Act: -0.0000

Data Index: 206724 (The Pile)

Max Activating Token Index: 724

Text #19

Max Range: 5.9225. Min Range: -5.9225

Max Act: 4.9924. Min Act: -0.0000

Data Index: 1169540 (The Pile)

Max Activating Token Index: 443