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

Dataset: The Pile

Neuron 3063 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.5989. Min Range: -5.5989

Max Act: 5.5989. Min Act: -0.0000

Data Index: 926469 (The Pile)

Max Activating Token Index: 647

Text #1

Max Range: 5.5989. Min Range: -5.5989

Max Act: 5.3666. Min Act: -0.0000

Data Index: 1105037 (The Pile)

Max Activating Token Index: 583

Text #2

Max Range: 5.5989. Min Range: -5.5989

Max Act: 5.0749. Min Act: -0.0000

Data Index: 1877183 (The Pile)

Max Activating Token Index: 191

Text #3

Max Range: 5.5989. Min Range: -5.5989

Max Act: 5.4428. Min Act: -0.0000

Data Index: 1687801 (The Pile)

Max Activating Token Index: 9

Text #4

Max Range: 5.5989. Min Range: -5.5989

Max Act: 5.2989. Min Act: -0.0000

Data Index: 220850 (The Pile)

Max Activating Token Index: 570

Text #5

Max Range: 5.5989. Min Range: -5.5989

Max Act: 5.1036. Min Act: -0.0000

Data Index: 1242788 (The Pile)

Max Activating Token Index: 398

Text #6

Max Range: 5.5989. Min Range: -5.5989

Max Act: 4.9543. Min Act: -0.0000

Data Index: 396126 (The Pile)

Max Activating Token Index: 111

Text #7

Max Range: 5.5989. Min Range: -5.5989

Max Act: 5.1160. Min Act: -0.0000

Data Index: 847100 (The Pile)

Max Activating Token Index: 321

Text #8

Max Range: 5.5989. Min Range: -5.5989

Max Act: 4.7326. Min Act: -0.0000

Data Index: 392482 (The Pile)

Max Activating Token Index: 159

Text #9

Max Range: 5.5989. Min Range: -5.5989

Max Act: 4.8619. Min Act: -0.0000

Data Index: 1921454 (The Pile)

Max Activating Token Index: 317

Text #10

Max Range: 5.5989. Min Range: -5.5989

Max Act: 4.8621. Min Act: -0.0000

Data Index: 489030 (The Pile)

Max Activating Token Index: 180

Text #11

Max Range: 5.5989. Min Range: -5.5989

Max Act: 4.8697. Min Act: -0.0000

Data Index: 441178 (The Pile)

Max Activating Token Index: 148

Text #12

Max Range: 5.5989. Min Range: -5.5989

Max Act: 4.8263. Min Act: -0.0000

Data Index: 735621 (The Pile)

Max Activating Token Index: 236

Text #13

Max Range: 5.5989. Min Range: -5.5989

Max Act: 4.9930. Min Act: -0.0000

Data Index: 662214 (The Pile)

Max Activating Token Index: 171

Text #14

Max Range: 5.5989. Min Range: -5.5989

Max Act: 4.9679. Min Act: -0.0000

Data Index: 1943414 (The Pile)

Max Activating Token Index: 823

Text #15

Max Range: 5.5989. Min Range: -5.5989

Max Act: 4.7870. Min Act: -0.0000

Data Index: 1072489 (The Pile)

Max Activating Token Index: 273

Text #16

Max Range: 5.5989. Min Range: -5.5989

Max Act: 4.3689. Min Act: -0.0000

Data Index: 202734 (The Pile)

Max Activating Token Index: 899

Text #17

Max Range: 5.5989. Min Range: -5.5989

Max Act: 4.7458. Min Act: -0.0000

Data Index: 1929406 (The Pile)

Max Activating Token Index: 256

Text #18

Max Range: 5.5989. Min Range: -5.5989

Max Act: 4.7266. Min Act: -0.0000

Data Index: 14034 (The Pile)

Max Activating Token Index: 500

Text #19

Max Range: 5.5989. Min Range: -5.5989

Max Act: 4.8704. Min Act: -0.0000

Data Index: 1617574 (The Pile)

Max Activating Token Index: 163