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

Dataset: The Pile

Neuron 1206 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9981. Min Range: -1.9981

Max Act: 1.9981. Min Act: -0.0000

Data Index: 1215728 (The Pile)

Max Activating Token Index: 852

Text #1

Max Range: 1.9981. Min Range: -1.9981

Max Act: 1.4606. Min Act: -0.0000

Data Index: 413166 (The Pile)

Max Activating Token Index: 902

Text #2

Max Range: 1.9981. Min Range: -1.9981

Max Act: 1.6543. Min Act: -0.0000

Data Index: 553805 (The Pile)

Max Activating Token Index: 960

Text #3

Max Range: 1.9981. Min Range: -1.9981

Max Act: 1.5277. Min Act: -0.0000

Data Index: 747769 (The Pile)

Max Activating Token Index: 168

Text #4

Max Range: 1.9981. Min Range: -1.9981

Max Act: 1.5810. Min Act: -0.0000

Data Index: 564639 (The Pile)

Max Activating Token Index: 712

Text #5

Max Range: 1.9981. Min Range: -1.9981

Max Act: 1.4800. Min Act: -0.0000

Data Index: 1435844 (The Pile)

Max Activating Token Index: 467

Text #6

Max Range: 1.9981. Min Range: -1.9981

Max Act: 1.5238. Min Act: -0.0000

Data Index: 1604274 (The Pile)

Max Activating Token Index: 49

Text #7

Max Range: 1.9981. Min Range: -1.9981

Max Act: 1.4331. Min Act: -0.0000

Data Index: 264435 (The Pile)

Max Activating Token Index: 190

Text #8

Max Range: 1.9981. Min Range: -1.9981

Max Act: 1.4391. Min Act: -0.0000

Data Index: 759838 (The Pile)

Max Activating Token Index: 74

Text #9

Max Range: 1.9981. Min Range: -1.9981

Max Act: 1.4969. Min Act: -0.0000

Data Index: 1027798 (The Pile)

Max Activating Token Index: 19

Text #10

Max Range: 1.9981. Min Range: -1.9981

Max Act: 1.5556. Min Act: -0.0000

Data Index: 1797186 (The Pile)

Max Activating Token Index: 404

Text #11

Max Range: 1.9981. Min Range: -1.9981

Max Act: 1.5536. Min Act: -0.0000

Data Index: 367244 (The Pile)

Max Activating Token Index: 408

Text #12

Max Range: 1.9981. Min Range: -1.9981

Max Act: 1.4417. Min Act: -0.0000

Data Index: 437365 (The Pile)

Max Activating Token Index: 551

Text #13

Max Range: 1.9981. Min Range: -1.9981

Max Act: 1.4249. Min Act: -0.0000

Data Index: 242820 (The Pile)

Max Activating Token Index: 514

Text #14

Max Range: 1.9981. Min Range: -1.9981

Max Act: 1.3523. Min Act: -0.0000

Data Index: 1345844 (The Pile)

Max Activating Token Index: 567

Text #15

Max Range: 1.9981. Min Range: -1.9981

Max Act: 1.4195. Min Act: -0.0000

Data Index: 1926080 (The Pile)

Max Activating Token Index: 552

Text #16

Max Range: 1.9981. Min Range: -1.9981

Max Act: 1.4143. Min Act: -0.0000

Data Index: 928478 (The Pile)

Max Activating Token Index: 496

Text #17

Max Range: 1.9981. Min Range: -1.9981

Max Act: 1.4744. Min Act: -0.0000

Data Index: 383908 (The Pile)

Max Activating Token Index: 403

Text #18

Max Range: 1.9981. Min Range: -1.9981

Max Act: 1.2521. Min Act: -0.0000

Data Index: 1627220 (The Pile)

Max Activating Token Index: 765

Text #19

Max Range: 1.9981. Min Range: -1.9981

Max Act: 1.3855. Min Act: -0.0000

Data Index: 1227413 (The Pile)

Max Activating Token Index: 389