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

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

Neuron 5072 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: 1.7930. Min Range: -1.7930

Max Act: 1.7930. Min Act: -0.0000

Data Index: 1142155 (C4 (Web Text))

Max Activating Token Index: 907

Text #1

Max Range: 1.7930. Min Range: -1.7930

Max Act: 1.7715. Min Act: -0.0000

Data Index: 260376 (C4 (Web Text))

Max Activating Token Index: 872

Text #2

Max Range: 1.7930. Min Range: -1.7930

Max Act: 1.7184. Min Act: -0.0000

Data Index: 1193365 (C4 (Web Text))

Max Activating Token Index: 326

Text #3

Max Range: 1.7930. Min Range: -1.7930

Max Act: 1.6844. Min Act: -0.0000

Data Index: 1295644 (C4 (Web Text))

Max Activating Token Index: 617

Text #4

Max Range: 1.7930. Min Range: -1.7930

Max Act: 1.5905. Min Act: -0.0000

Data Index: 1053884 (C4 (Web Text))

Max Activating Token Index: 477

Text #5

Max Range: 1.7930. Min Range: -1.7930

Max Act: 1.5394. Min Act: -0.0000

Data Index: 968930 (C4 (Web Text))

Max Activating Token Index: 786

Text #6

Max Range: 1.7930. Min Range: -1.7930

Max Act: 1.4669. Min Act: -0.0000

Data Index: 1318688 (C4 (Web Text))

Max Activating Token Index: 291

Text #7

Max Range: 1.7930. Min Range: -1.7930

Max Act: 1.4683. Min Act: -0.0000

Data Index: 1452623 (Python Code)

Max Activating Token Index: 952

Text #8

Max Range: 1.7930. Min Range: -1.7930

Max Act: 1.3804. Min Act: -0.0000

Data Index: 1518915 (Python Code)

Max Activating Token Index: 541

Text #9

Max Range: 1.7930. Min Range: -1.7930

Max Act: 1.4607. Min Act: -0.0000

Data Index: 1402911 (Python Code)

Max Activating Token Index: 876

Text #10

Max Range: 1.7930. Min Range: -1.7930

Max Act: 1.4499. Min Act: -0.0000

Data Index: 651570 (C4 (Web Text))

Max Activating Token Index: 885

Text #11

Max Range: 1.7930. Min Range: -1.7930

Max Act: 1.4183. Min Act: -0.0000

Data Index: 1434232 (Python Code)

Max Activating Token Index: 442

Text #12

Max Range: 1.7930. Min Range: -1.7930

Max Act: 1.4164. Min Act: -0.0000

Data Index: 1487986 (Python Code)

Max Activating Token Index: 417

Text #13

Max Range: 1.7930. Min Range: -1.7930

Max Act: 1.4005. Min Act: -0.0000

Data Index: 1488366 (Python Code)

Max Activating Token Index: 380

Text #14

Max Range: 1.7930. Min Range: -1.7930

Max Act: 1.3992. Min Act: -0.0000

Data Index: 1502181 (Python Code)

Max Activating Token Index: 411

Text #15

Max Range: 1.7930. Min Range: -1.7930

Max Act: 1.3907. Min Act: -0.0000

Data Index: 1536578 (Python Code)

Max Activating Token Index: 634

Text #16

Max Range: 1.7930. Min Range: -1.7930

Max Act: 1.3811. Min Act: -0.0000

Data Index: 1567530 (Python Code)

Max Activating Token Index: 505

Text #17

Max Range: 1.7930. Min Range: -1.7930

Max Act: 1.3770. Min Act: -0.0000

Data Index: 1567670 (Python Code)

Max Activating Token Index: 484

Text #18

Max Range: 1.7930. Min Range: -1.7930

Max Act: 1.3880. Min Act: -0.0000

Data Index: 1386074 (Python Code)

Max Activating Token Index: 795

Text #19

Max Range: 1.7930. Min Range: -1.7930

Max Act: 1.3468. Min Act: -0.0000

Data Index: 1413153 (Python Code)

Max Activating Token Index: 960