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

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

Neuron 4616 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.7422. Min Range: -0.7422

Max Act: 0.7422. Min Act: -0.0000

Data Index: 1623655 (Python Code)

Max Activating Token Index: 308

Text #1

Max Range: 0.7422. Min Range: -0.7422

Max Act: 0.6631. Min Act: -0.0000

Data Index: 53986 (C4 (Web Text))

Max Activating Token Index: 476

Text #2

Max Range: 0.7422. Min Range: -0.7422

Max Act: 0.6065. Min Act: -0.0000

Data Index: 1563397 (Python Code)

Max Activating Token Index: 219

Text #3

Max Range: 0.7422. Min Range: -0.7422

Max Act: 0.6461. Min Act: -0.0000

Data Index: 1133951 (C4 (Web Text))

Max Activating Token Index: 53

Text #4

Max Range: 0.7422. Min Range: -0.7422

Max Act: 0.6276. Min Act: -0.0000

Data Index: 31040 (C4 (Web Text))

Max Activating Token Index: 975

Text #5

Max Range: 0.7422. Min Range: -0.7422

Max Act: 0.6329. Min Act: -0.0000

Data Index: 1566249 (Python Code)

Max Activating Token Index: 575

Text #6

Max Range: 0.7422. Min Range: -0.7422

Max Act: 0.6490. Min Act: -0.0000

Data Index: 1179804 (C4 (Web Text))

Max Activating Token Index: 118

Text #7

Max Range: 0.7422. Min Range: -0.7422

Max Act: 0.6260. Min Act: -0.0000

Data Index: 330888 (C4 (Web Text))

Max Activating Token Index: 557

Text #8

Max Range: 0.7422. Min Range: -0.7422

Max Act: 0.6049. Min Act: -0.0001

Data Index: 1621372 (Python Code)

Max Activating Token Index: 135

Text #9

Max Range: 0.7422. Min Range: -0.7422

Max Act: 0.6171. Min Act: -0.0000

Data Index: 415060 (C4 (Web Text))

Max Activating Token Index: 450

Text #10

Max Range: 0.7422. Min Range: -0.7422

Max Act: 0.6069. Min Act: -0.0000

Data Index: 291528 (C4 (Web Text))

Max Activating Token Index: 502

Text #11

Max Range: 0.7422. Min Range: -0.7422

Max Act: 0.6037. Min Act: -0.0000

Data Index: 234416 (C4 (Web Text))

Max Activating Token Index: 11

Text #12

Max Range: 0.7422. Min Range: -0.7422

Max Act: 0.5887. Min Act: -0.0000

Data Index: 643804 (C4 (Web Text))

Max Activating Token Index: 697

Text #13

Max Range: 0.7422. Min Range: -0.7422

Max Act: 0.6194. Min Act: -0.0000

Data Index: 777715 (C4 (Web Text))

Max Activating Token Index: 687

Text #14

Max Range: 0.7422. Min Range: -0.7422

Max Act: 0.5792. Min Act: -0.0000

Data Index: 822030 (C4 (Web Text))

Max Activating Token Index: 493

Text #15

Max Range: 0.7422. Min Range: -0.7422

Max Act: 0.6720. Min Act: -0.0001

Data Index: 1565175 (Python Code)

Max Activating Token Index: 227

Text #16

Max Range: 0.7422. Min Range: -0.7422

Max Act: 0.5923. Min Act: -0.0000

Data Index: 864674 (C4 (Web Text))

Max Activating Token Index: 10

Text #17

Max Range: 0.7422. Min Range: -0.7422

Max Act: 0.5853. Min Act: -0.0000

Data Index: 597136 (C4 (Web Text))

Max Activating Token Index: 939

Text #18

Max Range: 0.7422. Min Range: -0.7422

Max Act: 0.6065. Min Act: -0.0000

Data Index: 392816 (C4 (Web Text))

Max Activating Token Index: 511

Text #19

Max Range: 0.7422. Min Range: -0.7422

Max Act: 0.5795. Min Act: -0.0000

Data Index: 273839 (C4 (Web Text))

Max Activating Token Index: 168