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

Dataset: The Pile

Neuron 4444 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: 1.4396. Min Range: -1.4396

Max Act: 1.3082. Min Act: -0.0000

Data Index: 1432847 (The Pile)

Max Activating Token Index: 837

Text #1

Max Range: 1.4396. Min Range: -1.4396

Max Act: 1.4396. Min Act: -0.0000

Data Index: 117346 (The Pile)

Max Activating Token Index: 460

Text #2

Max Range: 1.4396. Min Range: -1.4396

Max Act: 1.3136. Min Act: -0.0000

Data Index: 1464420 (The Pile)

Max Activating Token Index: 208

Text #3

Max Range: 1.4396. Min Range: -1.4396

Max Act: 1.3214. Min Act: -0.0000

Data Index: 642197 (The Pile)

Max Activating Token Index: 404

Text #4

Max Range: 1.4396. Min Range: -1.4396

Max Act: 1.2959. Min Act: -0.0000

Data Index: 1935310 (The Pile)

Max Activating Token Index: 334

Text #5

Max Range: 1.4396. Min Range: -1.4396

Max Act: 1.0705. Min Act: -0.0000

Data Index: 329362 (The Pile)

Max Activating Token Index: 971

Text #6

Max Range: 1.4396. Min Range: -1.4396

Max Act: 1.2267. Min Act: -0.0000

Data Index: 208664 (The Pile)

Max Activating Token Index: 721

Text #7

Max Range: 1.4396. Min Range: -1.4396

Max Act: 1.1345. Min Act: -0.0000

Data Index: 898889 (The Pile)

Max Activating Token Index: 141

Text #8

Max Range: 1.4396. Min Range: -1.4396

Max Act: 1.2574. Min Act: -0.0000

Data Index: 1670778 (The Pile)

Max Activating Token Index: 1004

Text #9

Max Range: 1.4396. Min Range: -1.4396

Max Act: 1.2041. Min Act: -0.0000

Data Index: 1073859 (The Pile)

Max Activating Token Index: 769

Text #10

Max Range: 1.4396. Min Range: -1.4396

Max Act: 1.1011. Min Act: -0.0000

Data Index: 891060 (The Pile)

Max Activating Token Index: 321

Text #11

Max Range: 1.4396. Min Range: -1.4396

Max Act: 1.1075. Min Act: -0.0000

Data Index: 89450 (The Pile)

Max Activating Token Index: 58

Text #12

Max Range: 1.4396. Min Range: -1.4396

Max Act: 1.0937. Min Act: -0.0000

Data Index: 963015 (The Pile)

Max Activating Token Index: 210

Text #13

Max Range: 1.4396. Min Range: -1.4396

Max Act: 1.0754. Min Act: -0.0000

Data Index: 1405161 (The Pile)

Max Activating Token Index: 137

Text #14

Max Range: 1.4396. Min Range: -1.4396

Max Act: 1.1115. Min Act: -0.0000

Data Index: 1655690 (The Pile)

Max Activating Token Index: 808

Text #15

Max Range: 1.4396. Min Range: -1.4396

Max Act: 1.1263. Min Act: -0.0000

Data Index: 843484 (The Pile)

Max Activating Token Index: 956

Text #16

Max Range: 1.4396. Min Range: -1.4396

Max Act: 1.0154. Min Act: -0.0000

Data Index: 874487 (The Pile)

Max Activating Token Index: 226

Text #17

Max Range: 1.4396. Min Range: -1.4396

Max Act: 1.0806. Min Act: -0.0000

Data Index: 606424 (The Pile)

Max Activating Token Index: 18

Text #18

Max Range: 1.4396. Min Range: -1.4396

Max Act: 0.9952. Min Act: -0.0000

Data Index: 1807857 (The Pile)

Max Activating Token Index: 826

Text #19

Max Range: 1.4396. Min Range: -1.4396

Max Act: 1.0154. Min Act: -0.0000

Data Index: 1430996 (The Pile)

Max Activating Token Index: 557