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

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

Neuron 2503 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1066. Min Range: -1.1066

Max Act: 1.1066. Min Act: -0.0000

Data Index: 896464 (C4 (Web Text))

Max Activating Token Index: 67

Text #1

Max Range: 1.1066. Min Range: -1.1066

Max Act: 0.9739. Min Act: -0.0000

Data Index: 576009 (C4 (Web Text))

Max Activating Token Index: 529

Text #2

Max Range: 1.1066. Min Range: -1.1066

Max Act: 0.8358. Min Act: -0.0000

Data Index: 628866 (C4 (Web Text))

Max Activating Token Index: 785

Text #3

Max Range: 1.1066. Min Range: -1.1066

Max Act: 0.9363. Min Act: -0.0000

Data Index: 393505 (C4 (Web Text))

Max Activating Token Index: 301

Text #4

Max Range: 1.1066. Min Range: -1.1066

Max Act: 0.9006. Min Act: -0.0000

Data Index: 132481 (C4 (Web Text))

Max Activating Token Index: 786

Text #5

Max Range: 1.1066. Min Range: -1.1066

Max Act: 0.9519. Min Act: -0.0000

Data Index: 618349 (C4 (Web Text))

Max Activating Token Index: 66

Text #6

Max Range: 1.1066. Min Range: -1.1066

Max Act: 0.8919. Min Act: -0.0000

Data Index: 94422 (C4 (Web Text))

Max Activating Token Index: 361

Text #7

Max Range: 1.1066. Min Range: -1.1066

Max Act: 0.8616. Min Act: -0.0000

Data Index: 870411 (C4 (Web Text))

Max Activating Token Index: 97

Text #8

Max Range: 1.1066. Min Range: -1.1066

Max Act: 0.7576. Min Act: -0.0000

Data Index: 101911 (C4 (Web Text))

Max Activating Token Index: 696

Text #9

Max Range: 1.1066. Min Range: -1.1066

Max Act: 0.7795. Min Act: -0.0000

Data Index: 899594 (C4 (Web Text))

Max Activating Token Index: 790

Text #10

Max Range: 1.1066. Min Range: -1.1066

Max Act: 0.8010. Min Act: -0.0000

Data Index: 98135 (C4 (Web Text))

Max Activating Token Index: 82

Text #11

Max Range: 1.1066. Min Range: -1.1066

Max Act: 0.7645. Min Act: -0.0000

Data Index: 1048445 (C4 (Web Text))

Max Activating Token Index: 696

Text #12

Max Range: 1.1066. Min Range: -1.1066

Max Act: 0.7349. Min Act: -0.0000

Data Index: 255335 (C4 (Web Text))

Max Activating Token Index: 155

Text #13

Max Range: 1.1066. Min Range: -1.1066

Max Act: 0.7854. Min Act: -0.0000

Data Index: 1199507 (C4 (Web Text))

Max Activating Token Index: 92

Text #14

Max Range: 1.1066. Min Range: -1.1066

Max Act: 0.7337. Min Act: -0.0000

Data Index: 889061 (C4 (Web Text))

Max Activating Token Index: 1021

Text #15

Max Range: 1.1066. Min Range: -1.1066

Max Act: 0.7040. Min Act: -0.0000

Data Index: 1143460 (C4 (Web Text))

Max Activating Token Index: 689

Text #16

Max Range: 1.1066. Min Range: -1.1066

Max Act: 0.7207. Min Act: -0.0000

Data Index: 1500104 (Python Code)

Max Activating Token Index: 191

Text #17

Max Range: 1.1066. Min Range: -1.1066

Max Act: 0.6710. Min Act: -0.0000

Data Index: 110622 (C4 (Web Text))

Max Activating Token Index: 286

Text #18

Max Range: 1.1066. Min Range: -1.1066

Max Act: 0.7485. Min Act: -0.0000

Data Index: 564334 (C4 (Web Text))

Max Activating Token Index: 355

Text #19

Max Range: 1.1066. Min Range: -1.1066

Max Act: 0.6714. Min Act: -0.0000

Data Index: 141833 (C4 (Web Text))

Max Activating Token Index: 735