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

Dataset: The Pile

Neuron 4059 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5750. Min Range: -0.5750

Max Act: 0.5697. Min Act: -0.0000

Data Index: 1485619 (The Pile)

Max Activating Token Index: 115

Text #1

Max Range: 0.5750. Min Range: -0.5750

Max Act: 0.5741. Min Act: -0.0000

Data Index: 604054 (The Pile)

Max Activating Token Index: 239

Text #2

Max Range: 0.5750. Min Range: -0.5750

Max Act: 0.5585. Min Act: -0.0000

Data Index: 24542 (The Pile)

Max Activating Token Index: 966

Text #3

Max Range: 0.5750. Min Range: -0.5750

Max Act: 0.5022. Min Act: -0.0000

Data Index: 776749 (The Pile)

Max Activating Token Index: 593

Text #4

Max Range: 0.5750. Min Range: -0.5750

Max Act: 0.5500. Min Act: -0.0000

Data Index: 748195 (The Pile)

Max Activating Token Index: 94

Text #5

Max Range: 0.5750. Min Range: -0.5750

Max Act: 0.5191. Min Act: -0.0000

Data Index: 446212 (The Pile)

Max Activating Token Index: 662

Text #6

Max Range: 0.5750. Min Range: -0.5750

Max Act: 0.5556. Min Act: -0.0000

Data Index: 1157577 (The Pile)

Max Activating Token Index: 913

Text #7

Max Range: 0.5750. Min Range: -0.5750

Max Act: 0.4864. Min Act: -0.0000

Data Index: 1637654 (The Pile)

Max Activating Token Index: 268

Text #8

Max Range: 0.5750. Min Range: -0.5750

Max Act: 0.5202. Min Act: -0.0000

Data Index: 1902559 (The Pile)

Max Activating Token Index: 72

Text #9

Max Range: 0.5750. Min Range: -0.5750

Max Act: 0.5201. Min Act: -0.0000

Data Index: 530851 (The Pile)

Max Activating Token Index: 928

Text #10

Max Range: 0.5750. Min Range: -0.5750

Max Act: 0.5324. Min Act: -0.0000

Data Index: 338471 (The Pile)

Max Activating Token Index: 833

Text #11

Max Range: 0.5750. Min Range: -0.5750

Max Act: 0.5046. Min Act: -0.0000

Data Index: 970855 (The Pile)

Max Activating Token Index: 399

Text #12

Max Range: 0.5750. Min Range: -0.5750

Max Act: 0.5750. Min Act: -0.0000

Data Index: 1245057 (The Pile)

Max Activating Token Index: 163

Text #13

Max Range: 0.5750. Min Range: -0.5750

Max Act: 0.5176. Min Act: -0.0000

Data Index: 1331738 (The Pile)

Max Activating Token Index: 487

Text #14

Max Range: 0.5750. Min Range: -0.5750

Max Act: 0.4985. Min Act: -0.0000

Data Index: 1901065 (The Pile)

Max Activating Token Index: 7

Text #15

Max Range: 0.5750. Min Range: -0.5750

Max Act: 0.5076. Min Act: -0.0000

Data Index: 1013101 (The Pile)

Max Activating Token Index: 352

Text #16

Max Range: 0.5750. Min Range: -0.5750

Max Act: 0.5092. Min Act: -0.0000

Data Index: 465086 (The Pile)

Max Activating Token Index: 380

Text #17

Max Range: 0.5750. Min Range: -0.5750

Max Act: 0.5061. Min Act: -0.0000

Data Index: 166920 (The Pile)

Max Activating Token Index: 173

Text #18

Max Range: 0.5750. Min Range: -0.5750

Max Act: 0.5193. Min Act: -0.0000

Data Index: 610432 (The Pile)

Max Activating Token Index: 180

Text #19

Max Range: 0.5750. Min Range: -0.5750

Max Act: 0.4662. Min Act: -0.0000

Data Index: 644155 (The Pile)

Max Activating Token Index: 399