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

Dataset: The Pile

Neuron 2175 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7452. Min Range: -0.7452

Max Act: 0.7191. Min Act: -0.0000

Data Index: 236156 (The Pile)

Max Activating Token Index: 92

Text #1

Max Range: 0.7452. Min Range: -0.7452

Max Act: 0.5053. Min Act: 0.0000

Data Index: 1577560 (The Pile)

Max Activating Token Index: 804

Text #2

Max Range: 0.7452. Min Range: -0.7452

Max Act: 0.6753. Min Act: -0.0000

Data Index: 1663921 (The Pile)

Max Activating Token Index: 419

Text #3

Max Range: 0.7452. Min Range: -0.7452

Max Act: 0.6413. Min Act: -0.0000

Data Index: 1333119 (The Pile)

Max Activating Token Index: 266

Text #4

Max Range: 0.7452. Min Range: -0.7452

Max Act: 0.6620. Min Act: -0.0000

Data Index: 1116223 (The Pile)

Max Activating Token Index: 380

Text #5

Max Range: 0.7452. Min Range: -0.7452

Max Act: 0.7452. Min Act: -0.0000

Data Index: 68654 (The Pile)

Max Activating Token Index: 295

Text #6

Max Range: 0.7452. Min Range: -0.7452

Max Act: 0.5531. Min Act: -0.0000

Data Index: 355946 (The Pile)

Max Activating Token Index: 521

Text #7

Max Range: 0.7452. Min Range: -0.7452

Max Act: 0.5199. Min Act: -0.0000

Data Index: 13575 (The Pile)

Max Activating Token Index: 942

Text #8

Max Range: 0.7452. Min Range: -0.7452

Max Act: 0.6196. Min Act: -0.0000

Data Index: 1324696 (The Pile)

Max Activating Token Index: 155

Text #9

Max Range: 0.7452. Min Range: -0.7452

Max Act: 0.6155. Min Act: -0.0000

Data Index: 1438099 (The Pile)

Max Activating Token Index: 678

Text #10

Max Range: 0.7452. Min Range: -0.7452

Max Act: 0.5136. Min Act: -0.0000

Data Index: 1861164 (The Pile)

Max Activating Token Index: 489

Text #11

Max Range: 0.7452. Min Range: -0.7452

Max Act: 0.5632. Min Act: -0.0000

Data Index: 1591443 (The Pile)

Max Activating Token Index: 444

Text #12

Max Range: 0.7452. Min Range: -0.7452

Max Act: 0.4712. Min Act: -0.0000

Data Index: 1957636 (The Pile)

Max Activating Token Index: 429

Text #13

Max Range: 0.7452. Min Range: -0.7452

Max Act: 0.4507. Min Act: -0.0000

Data Index: 1667910 (The Pile)

Max Activating Token Index: 891

Text #14

Max Range: 0.7452. Min Range: -0.7452

Max Act: 0.5414. Min Act: -0.0000

Data Index: 315299 (The Pile)

Max Activating Token Index: 301

Text #15

Max Range: 0.7452. Min Range: -0.7452

Max Act: 0.3289. Min Act: -0.0000

Data Index: 1864883 (The Pile)

Max Activating Token Index: 981

Text #16

Max Range: 0.7452. Min Range: -0.7452

Max Act: 0.4724. Min Act: -0.0000

Data Index: 1317236 (The Pile)

Max Activating Token Index: 638

Text #17

Max Range: 0.7452. Min Range: -0.7452

Max Act: 0.4814. Min Act: -0.0000

Data Index: 910731 (The Pile)

Max Activating Token Index: 766

Text #18

Max Range: 0.7452. Min Range: -0.7452

Max Act: 0.4480. Min Act: -0.0000

Data Index: 143067 (The Pile)

Max Activating Token Index: 540

Text #19

Max Range: 0.7452. Min Range: -0.7452

Max Act: 0.4870. Min Act: -0.0000

Data Index: 225607 (The Pile)

Max Activating Token Index: 755