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

Dataset: The Pile

Neuron 467 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5119. Min Range: -0.5119

Max Act: 0.5119. Min Act: -0.0000

Data Index: 1899233 (The Pile)

Max Activating Token Index: 788

Text #1

Max Range: 0.5119. Min Range: -0.5119

Max Act: 0.3188. Min Act: -0.0000

Data Index: 1579198 (The Pile)

Max Activating Token Index: 288

Text #2

Max Range: 0.5119. Min Range: -0.5119

Max Act: 0.3059. Min Act: -0.0000

Data Index: 74479 (The Pile)

Max Activating Token Index: 87

Text #3

Max Range: 0.5119. Min Range: -0.5119

Max Act: 0.2842. Min Act: -0.0000

Data Index: 300065 (The Pile)

Max Activating Token Index: 288

Text #4

Max Range: 0.5119. Min Range: -0.5119

Max Act: 0.2687. Min Act: -0.0000

Data Index: 881762 (The Pile)

Max Activating Token Index: 68

Text #5

Max Range: 0.5119. Min Range: -0.5119

Max Act: 0.2280. Min Act: -0.0000

Data Index: 11959 (The Pile)

Max Activating Token Index: 900

Text #6

Max Range: 0.5119. Min Range: -0.5119

Max Act: 0.2459. Min Act: -0.0000

Data Index: 371679 (The Pile)

Max Activating Token Index: 360

Text #7

Max Range: 0.5119. Min Range: -0.5119

Max Act: 0.2600. Min Act: -0.0000

Data Index: 1620454 (The Pile)

Max Activating Token Index: 523

Text #8

Max Range: 0.5119. Min Range: -0.5119

Max Act: 0.2519. Min Act: -0.0000

Data Index: 190248 (The Pile)

Max Activating Token Index: 497

Text #9

Max Range: 0.5119. Min Range: -0.5119

Max Act: 0.2397. Min Act: -0.0000

Data Index: 343088 (The Pile)

Max Activating Token Index: 269

Text #10

Max Range: 0.5119. Min Range: -0.5119

Max Act: 0.2459. Min Act: -0.0000

Data Index: 264166 (The Pile)

Max Activating Token Index: 149

Text #11

Max Range: 0.5119. Min Range: -0.5119

Max Act: 0.2442. Min Act: -0.0000

Data Index: 759856 (The Pile)

Max Activating Token Index: 230

Text #12

Max Range: 0.5119. Min Range: -0.5119

Max Act: 0.2514. Min Act: -0.0000

Data Index: 1069833 (The Pile)

Max Activating Token Index: 185

Text #13

Max Range: 0.5119. Min Range: -0.5119

Max Act: 0.2272. Min Act: -0.0000

Data Index: 735792 (The Pile)

Max Activating Token Index: 503

Text #14

Max Range: 0.5119. Min Range: -0.5119

Max Act: 0.2393. Min Act: -0.0000

Data Index: 470097 (The Pile)

Max Activating Token Index: 848

Text #15

Max Range: 0.5119. Min Range: -0.5119

Max Act: 0.2473. Min Act: -0.0000

Data Index: 854237 (The Pile)

Max Activating Token Index: 506

Text #16

Max Range: 0.5119. Min Range: -0.5119

Max Act: 0.2365. Min Act: -0.0000

Data Index: 1039349 (The Pile)

Max Activating Token Index: 597

Text #17

Max Range: 0.5119. Min Range: -0.5119

Max Act: 0.2282. Min Act: -0.0000

Data Index: 1787590 (The Pile)

Max Activating Token Index: 413

Text #18

Max Range: 0.5119. Min Range: -0.5119

Max Act: 0.2256. Min Act: -0.0000

Data Index: 326844 (The Pile)

Max Activating Token Index: 584

Text #19

Max Range: 0.5119. Min Range: -0.5119

Max Act: 0.2425. Min Act: -0.0000

Data Index: 147560 (The Pile)

Max Activating Token Index: 126