Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 4846 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.9205. Min Range: -0.9205

Max Act: 0.8482. Min Act: -0.0000

Data Index: 477635 (C4 (Web Text))

Max Activating Token Index: 249

Text #1

Max Range: 0.9205. Min Range: -0.9205

Max Act: 0.8396. Min Act: -0.0000

Data Index: 1253961 (C4 (Web Text))

Max Activating Token Index: 394

Text #2

Max Range: 0.9205. Min Range: -0.9205

Max Act: 0.8131. Min Act: -0.0000

Data Index: 508077 (C4 (Web Text))

Max Activating Token Index: 678

Text #3

Max Range: 0.9205. Min Range: -0.9205

Max Act: 0.9205. Min Act: -0.0000

Data Index: 380304 (C4 (Web Text))

Max Activating Token Index: 852

Text #4

Max Range: 0.9205. Min Range: -0.9205

Max Act: 0.7812. Min Act: -0.0000

Data Index: 776633 (C4 (Web Text))

Max Activating Token Index: 938

Text #5

Max Range: 0.9205. Min Range: -0.9205

Max Act: 0.7891. Min Act: -0.0000

Data Index: 1143889 (C4 (Web Text))

Max Activating Token Index: 578

Text #6

Max Range: 0.9205. Min Range: -0.9205

Max Act: 0.8098. Min Act: -0.0000

Data Index: 161004 (C4 (Web Text))

Max Activating Token Index: 401

Text #7

Max Range: 0.9205. Min Range: -0.9205

Max Act: 0.7530. Min Act: -0.0000

Data Index: 1128206 (C4 (Web Text))

Max Activating Token Index: 650

Text #8

Max Range: 0.9205. Min Range: -0.9205

Max Act: 0.7655. Min Act: -0.0000

Data Index: 383510 (C4 (Web Text))

Max Activating Token Index: 213

Text #9

Max Range: 0.9205. Min Range: -0.9205

Max Act: 0.7323. Min Act: -0.0000

Data Index: 1287701 (C4 (Web Text))

Max Activating Token Index: 59

Text #10

Max Range: 0.9205. Min Range: -0.9205

Max Act: 0.7684. Min Act: -0.0000

Data Index: 356300 (C4 (Web Text))

Max Activating Token Index: 672

Text #11

Max Range: 0.9205. Min Range: -0.9205

Max Act: 0.6734. Min Act: -0.0000

Data Index: 387561 (C4 (Web Text))

Max Activating Token Index: 766

Text #12

Max Range: 0.9205. Min Range: -0.9205

Max Act: 0.7140. Min Act: -0.0000

Data Index: 669907 (C4 (Web Text))

Max Activating Token Index: 67

Text #13

Max Range: 0.9205. Min Range: -0.9205

Max Act: 0.7161. Min Act: -0.0000

Data Index: 13307 (C4 (Web Text))

Max Activating Token Index: 482

Text #14

Max Range: 0.9205. Min Range: -0.9205

Max Act: 0.6834. Min Act: -0.0000

Data Index: 3605 (C4 (Web Text))

Max Activating Token Index: 397

Text #15

Max Range: 0.9205. Min Range: -0.9205

Max Act: 0.6846. Min Act: -0.0000

Data Index: 562498 (C4 (Web Text))

Max Activating Token Index: 228

Text #16

Max Range: 0.9205. Min Range: -0.9205

Max Act: 0.6290. Min Act: -0.0000

Data Index: 1348613 (C4 (Web Text))

Max Activating Token Index: 614

Text #17

Max Range: 0.9205. Min Range: -0.9205

Max Act: 0.6228. Min Act: -0.0000

Data Index: 547782 (C4 (Web Text))

Max Activating Token Index: 470

Text #18

Max Range: 0.9205. Min Range: -0.9205

Max Act: 0.6324. Min Act: -0.0000

Data Index: 440547 (C4 (Web Text))

Max Activating Token Index: 505

Text #19

Max Range: 0.9205. Min Range: -0.9205

Max Act: 0.5944. Min Act: -0.0000

Data Index: 1199891 (C4 (Web Text))

Max Activating Token Index: 389