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

Dataset: The Pile

Neuron 1115 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5527. Min Range: -0.5527

Max Act: 0.5527. Min Act: -0.0000

Data Index: 301638 (The Pile)

Max Activating Token Index: 137

Text #1

Max Range: 0.5527. Min Range: -0.5527

Max Act: 0.3509. Min Act: -0.0000

Data Index: 1166811 (The Pile)

Max Activating Token Index: 340

Text #2

Max Range: 0.5527. Min Range: -0.5527

Max Act: 0.2532. Min Act: -0.0000

Data Index: 711066 (The Pile)

Max Activating Token Index: 238

Text #3

Max Range: 0.5527. Min Range: -0.5527

Max Act: 0.3483. Min Act: -0.0000

Data Index: 1045487 (The Pile)

Max Activating Token Index: 178

Text #4

Max Range: 0.5527. Min Range: -0.5527

Max Act: 0.3744. Min Act: -0.0000

Data Index: 1604788 (The Pile)

Max Activating Token Index: 376

Text #5

Max Range: 0.5527. Min Range: -0.5527

Max Act: 0.3152. Min Act: -0.0000

Data Index: 1575393 (The Pile)

Max Activating Token Index: 580

Text #6

Max Range: 0.5527. Min Range: -0.5527

Max Act: 0.2974. Min Act: -0.0000

Data Index: 1005580 (The Pile)

Max Activating Token Index: 172

Text #7

Max Range: 0.5527. Min Range: -0.5527

Max Act: 0.2621. Min Act: -0.0000

Data Index: 1188985 (The Pile)

Max Activating Token Index: 34

Text #8

Max Range: 0.5527. Min Range: -0.5527

Max Act: 0.2679. Min Act: -0.0000

Data Index: 601594 (The Pile)

Max Activating Token Index: 112

Text #9

Max Range: 0.5527. Min Range: -0.5527

Max Act: 0.2559. Min Act: -0.0000

Data Index: 1021226 (The Pile)

Max Activating Token Index: 641

Text #10

Max Range: 0.5527. Min Range: -0.5527

Max Act: 0.2472. Min Act: -0.0000

Data Index: 405770 (The Pile)

Max Activating Token Index: 398

Text #11

Max Range: 0.5527. Min Range: -0.5527

Max Act: 0.2667. Min Act: -0.0000

Data Index: 225473 (The Pile)

Max Activating Token Index: 311

Text #12

Max Range: 0.5527. Min Range: -0.5527

Max Act: 0.2828. Min Act: -0.0000

Data Index: 284421 (The Pile)

Max Activating Token Index: 834

Text #13

Max Range: 0.5527. Min Range: -0.5527

Max Act: 0.1985. Min Act: -0.0000

Data Index: 304197 (The Pile)

Max Activating Token Index: 104

Text #14

Max Range: 0.5527. Min Range: -0.5527

Max Act: 0.2169. Min Act: -0.0000

Data Index: 110976 (The Pile)

Max Activating Token Index: 254

Text #15

Max Range: 0.5527. Min Range: -0.5527

Max Act: 0.2364. Min Act: -0.0000

Data Index: 438275 (The Pile)

Max Activating Token Index: 191

Text #16

Max Range: 0.5527. Min Range: -0.5527

Max Act: 0.2130. Min Act: -0.0000

Data Index: 703839 (The Pile)

Max Activating Token Index: 63

Text #17

Max Range: 0.5527. Min Range: -0.5527

Max Act: 0.2485. Min Act: -0.0000

Data Index: 399435 (The Pile)

Max Activating Token Index: 823

Text #18

Max Range: 0.5527. Min Range: -0.5527

Max Act: 0.1969. Min Act: -0.0000

Data Index: 1971003 (The Pile)

Max Activating Token Index: 148

Text #19

Max Range: 0.5527. Min Range: -0.5527

Max Act: 0.2307. Min Act: -0.0000

Data Index: 659981 (The Pile)

Max Activating Token Index: 89