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

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

Neuron 3928 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6634. Min Range: -0.6634

Max Act: 0.6634. Min Act: -0.0001

Data Index: 379953 (C4 (Web Text))

Max Activating Token Index: 91

Text #1

Max Range: 0.6634. Min Range: -0.6634

Max Act: 0.5219. Min Act: -0.0001

Data Index: 672954 (C4 (Web Text))

Max Activating Token Index: 331

Text #2

Max Range: 0.6634. Min Range: -0.6634

Max Act: 0.5434. Min Act: -0.0001

Data Index: 95631 (C4 (Web Text))

Max Activating Token Index: 391

Text #3

Max Range: 0.6634. Min Range: -0.6634

Max Act: 0.5676. Min Act: -0.0001

Data Index: 159773 (C4 (Web Text))

Max Activating Token Index: 894

Text #4

Max Range: 0.6634. Min Range: -0.6634

Max Act: 0.4790. Min Act: -0.0000

Data Index: 1091295 (C4 (Web Text))

Max Activating Token Index: 583

Text #5

Max Range: 0.6634. Min Range: -0.6634

Max Act: 0.5385. Min Act: -0.0001

Data Index: 79885 (C4 (Web Text))

Max Activating Token Index: 71

Text #6

Max Range: 0.6634. Min Range: -0.6634

Max Act: 0.5072. Min Act: -0.0001

Data Index: 543829 (C4 (Web Text))

Max Activating Token Index: 168

Text #7

Max Range: 0.6634. Min Range: -0.6634

Max Act: 0.5207. Min Act: -0.0001

Data Index: 672826 (C4 (Web Text))

Max Activating Token Index: 440

Text #8

Max Range: 0.6634. Min Range: -0.6634

Max Act: 0.4654. Min Act: -0.0001

Data Index: 1307937 (C4 (Web Text))

Max Activating Token Index: 473

Text #9

Max Range: 0.6634. Min Range: -0.6634

Max Act: 0.4154. Min Act: -0.0001

Data Index: 594949 (C4 (Web Text))

Max Activating Token Index: 771

Text #10

Max Range: 0.6634. Min Range: -0.6634

Max Act: 0.4166. Min Act: -0.0001

Data Index: 675861 (C4 (Web Text))

Max Activating Token Index: 112

Text #11

Max Range: 0.6634. Min Range: -0.6634

Max Act: 0.5154. Min Act: -0.0001

Data Index: 571029 (C4 (Web Text))

Max Activating Token Index: 498

Text #12

Max Range: 0.6634. Min Range: -0.6634

Max Act: 0.4572. Min Act: -0.0000

Data Index: 911251 (C4 (Web Text))

Max Activating Token Index: 857

Text #13

Max Range: 0.6634. Min Range: -0.6634

Max Act: 0.4099. Min Act: -0.0001

Data Index: 991451 (C4 (Web Text))

Max Activating Token Index: 513

Text #14

Max Range: 0.6634. Min Range: -0.6634

Max Act: 0.4192. Min Act: -0.0001

Data Index: 757472 (C4 (Web Text))

Max Activating Token Index: 527

Text #15

Max Range: 0.6634. Min Range: -0.6634

Max Act: 0.4682. Min Act: -0.0001

Data Index: 1251985 (C4 (Web Text))

Max Activating Token Index: 386

Text #16

Max Range: 0.6634. Min Range: -0.6634

Max Act: 0.3441. Min Act: -0.0000

Data Index: 648898 (C4 (Web Text))

Max Activating Token Index: 766

Text #17

Max Range: 0.6634. Min Range: -0.6634

Max Act: 0.3498. Min Act: -0.0001

Data Index: 916712 (C4 (Web Text))

Max Activating Token Index: 180

Text #18

Max Range: 0.6634. Min Range: -0.6634

Max Act: 0.4104. Min Act: -0.0001

Data Index: 262845 (C4 (Web Text))

Max Activating Token Index: 872

Text #19

Max Range: 0.6634. Min Range: -0.6634

Max Act: 0.3974. Min Act: -0.0001

Data Index: 252640 (C4 (Web Text))

Max Activating Token Index: 231