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

Dataset: The Pile

Neuron 3716 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: 0.2918. Min Range: -0.2918

Max Act: 0.2908. Min Act: -0.0000

Data Index: 1927599 (The Pile)

Max Activating Token Index: 950

Text #1

Max Range: 0.2918. Min Range: -0.2918

Max Act: 0.2918. Min Act: -0.0000

Data Index: 856152 (The Pile)

Max Activating Token Index: 715

Text #2

Max Range: 0.2918. Min Range: -0.2918

Max Act: 0.2726. Min Act: -0.0000

Data Index: 477053 (The Pile)

Max Activating Token Index: 21

Text #3

Max Range: 0.2918. Min Range: -0.2918

Max Act: 0.2843. Min Act: -0.0000

Data Index: 867595 (The Pile)

Max Activating Token Index: 83

Text #4

Max Range: 0.2918. Min Range: -0.2918

Max Act: 0.2606. Min Act: -0.0000

Data Index: 858063 (The Pile)

Max Activating Token Index: 84

Text #5

Max Range: 0.2918. Min Range: -0.2918

Max Act: 0.2739. Min Act: -0.0000

Data Index: 1296145 (The Pile)

Max Activating Token Index: 287

Text #6

Max Range: 0.2918. Min Range: -0.2918

Max Act: 0.2749. Min Act: -0.0000

Data Index: 1935564 (The Pile)

Max Activating Token Index: 763

Text #7

Max Range: 0.2918. Min Range: -0.2918

Max Act: 0.2587. Min Act: -0.0000

Data Index: 903533 (The Pile)

Max Activating Token Index: 12

Text #8

Max Range: 0.2918. Min Range: -0.2918

Max Act: 0.2614. Min Act: -0.0000

Data Index: 1004935 (The Pile)

Max Activating Token Index: 299

Text #9

Max Range: 0.2918. Min Range: -0.2918

Max Act: 0.2610. Min Act: -0.0000

Data Index: 828445 (The Pile)

Max Activating Token Index: 467

Text #10

Max Range: 0.2918. Min Range: -0.2918

Max Act: 0.2313. Min Act: -0.0000

Data Index: 1039304 (The Pile)

Max Activating Token Index: 601

Text #11

Max Range: 0.2918. Min Range: -0.2918

Max Act: 0.2511. Min Act: -0.0000

Data Index: 1723635 (The Pile)

Max Activating Token Index: 980

Text #12

Max Range: 0.2918. Min Range: -0.2918

Max Act: 0.2246. Min Act: -0.0000

Data Index: 1244061 (The Pile)

Max Activating Token Index: 1014

Text #13

Max Range: 0.2918. Min Range: -0.2918

Max Act: 0.2267. Min Act: -0.0000

Data Index: 1424868 (The Pile)

Max Activating Token Index: 363

Text #14

Max Range: 0.2918. Min Range: -0.2918

Max Act: 0.2545. Min Act: -0.0000

Data Index: 643401 (The Pile)

Max Activating Token Index: 869

Text #15

Max Range: 0.2918. Min Range: -0.2918

Max Act: 0.2538. Min Act: -0.0000

Data Index: 900127 (The Pile)

Max Activating Token Index: 380

Text #16

Max Range: 0.2918. Min Range: -0.2918

Max Act: 0.2290. Min Act: -0.0000

Data Index: 665786 (The Pile)

Max Activating Token Index: 498

Text #17

Max Range: 0.2918. Min Range: -0.2918

Max Act: 0.2269. Min Act: -0.0000

Data Index: 1846508 (The Pile)

Max Activating Token Index: 535

Text #18

Max Range: 0.2918. Min Range: -0.2918

Max Act: 0.2262. Min Act: -0.0000

Data Index: 1902435 (The Pile)

Max Activating Token Index: 244

Text #19

Max Range: 0.2918. Min Range: -0.2918

Max Act: 0.2265. Min Act: -0.0001

Data Index: 1105274 (The Pile)

Max Activating Token Index: 20