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

Dataset: The Pile

Neuron 3474 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: 0.6565. Min Range: -0.6565

Max Act: 0.6565. Min Act: -0.0000

Data Index: 693521 (The Pile)

Max Activating Token Index: 215

Text #1

Max Range: 0.6565. Min Range: -0.6565

Max Act: 0.5773. Min Act: -0.0000

Data Index: 564404 (The Pile)

Max Activating Token Index: 403

Text #2

Max Range: 0.6565. Min Range: -0.6565

Max Act: 0.5708. Min Act: -0.0000

Data Index: 944363 (The Pile)

Max Activating Token Index: 906

Text #3

Max Range: 0.6565. Min Range: -0.6565

Max Act: 0.5778. Min Act: -0.0000

Data Index: 223334 (The Pile)

Max Activating Token Index: 259

Text #4

Max Range: 0.6565. Min Range: -0.6565

Max Act: 0.5856. Min Act: -0.0000

Data Index: 470360 (The Pile)

Max Activating Token Index: 452

Text #5

Max Range: 0.6565. Min Range: -0.6565

Max Act: 0.5883. Min Act: -0.0000

Data Index: 1097763 (The Pile)

Max Activating Token Index: 759

Text #6

Max Range: 0.6565. Min Range: -0.6565

Max Act: 0.5857. Min Act: -0.0000

Data Index: 1050690 (The Pile)

Max Activating Token Index: 832

Text #7

Max Range: 0.6565. Min Range: -0.6565

Max Act: 0.5349. Min Act: -0.0000

Data Index: 955686 (The Pile)

Max Activating Token Index: 619

Text #8

Max Range: 0.6565. Min Range: -0.6565

Max Act: 0.6138. Min Act: -0.0000

Data Index: 1101332 (The Pile)

Max Activating Token Index: 720

Text #9

Max Range: 0.6565. Min Range: -0.6565

Max Act: 0.6019. Min Act: -0.0000

Data Index: 1477855 (The Pile)

Max Activating Token Index: 44

Text #10

Max Range: 0.6565. Min Range: -0.6565

Max Act: 0.5060. Min Act: -0.0000

Data Index: 525462 (The Pile)

Max Activating Token Index: 296

Text #11

Max Range: 0.6565. Min Range: -0.6565

Max Act: 0.5176. Min Act: -0.0000

Data Index: 980212 (The Pile)

Max Activating Token Index: 595

Text #12

Max Range: 0.6565. Min Range: -0.6565

Max Act: 0.5334. Min Act: -0.0000

Data Index: 946819 (The Pile)

Max Activating Token Index: 706

Text #13

Max Range: 0.6565. Min Range: -0.6565

Max Act: 0.4979. Min Act: -0.0000

Data Index: 189757 (The Pile)

Max Activating Token Index: 995

Text #14

Max Range: 0.6565. Min Range: -0.6565

Max Act: 0.5266. Min Act: -0.0000

Data Index: 1625601 (The Pile)

Max Activating Token Index: 187

Text #15

Max Range: 0.6565. Min Range: -0.6565

Max Act: 0.4914. Min Act: -0.0000

Data Index: 1270937 (The Pile)

Max Activating Token Index: 84

Text #16

Max Range: 0.6565. Min Range: -0.6565

Max Act: 0.4936. Min Act: -0.0000

Data Index: 1127926 (The Pile)

Max Activating Token Index: 578

Text #17

Max Range: 0.6565. Min Range: -0.6565

Max Act: 0.5137. Min Act: -0.0000

Data Index: 1438420 (The Pile)

Max Activating Token Index: 786

Text #18

Max Range: 0.6565. Min Range: -0.6565

Max Act: 0.4633. Min Act: -0.0000

Data Index: 902421 (The Pile)

Max Activating Token Index: 593

Text #19

Max Range: 0.6565. Min Range: -0.6565

Max Act: 0.4653. Min Act: -0.0000

Data Index: 1804695 (The Pile)

Max Activating Token Index: 604