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

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

Neuron 2741 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8446. Min Range: -0.8446

Max Act: 0.8446. Min Act: -0.0000

Data Index: 1470572 (Python Code)

Max Activating Token Index: 184

Text #1

Max Range: 0.8446. Min Range: -0.8446

Max Act: 0.8322. Min Act: -0.0000

Data Index: 1370881 (Python Code)

Max Activating Token Index: 40

Text #2

Max Range: 0.8446. Min Range: -0.8446

Max Act: 0.7929. Min Act: -0.0000

Data Index: 1598903 (Python Code)

Max Activating Token Index: 806

Text #3

Max Range: 0.8446. Min Range: -0.8446

Max Act: 0.8084. Min Act: -0.0000

Data Index: 1591953 (Python Code)

Max Activating Token Index: 688

Text #4

Max Range: 0.8446. Min Range: -0.8446

Max Act: 0.7628. Min Act: -0.0000

Data Index: 1525727 (Python Code)

Max Activating Token Index: 92

Text #5

Max Range: 0.8446. Min Range: -0.8446

Max Act: 0.7576. Min Act: -0.0000

Data Index: 1466681 (Python Code)

Max Activating Token Index: 526

Text #6

Max Range: 0.8446. Min Range: -0.8446

Max Act: 0.6716. Min Act: -0.0000

Data Index: 1625342 (Python Code)

Max Activating Token Index: 121

Text #7

Max Range: 0.8446. Min Range: -0.8446

Max Act: 0.6824. Min Act: -0.0000

Data Index: 1529021 (Python Code)

Max Activating Token Index: 29

Text #8

Max Range: 0.8446. Min Range: -0.8446

Max Act: 0.6612. Min Act: -0.0000

Data Index: 1601545 (Python Code)

Max Activating Token Index: 550

Text #9

Max Range: 0.8446. Min Range: -0.8446

Max Act: 0.6820. Min Act: -0.0000

Data Index: 1506349 (Python Code)

Max Activating Token Index: 346

Text #10

Max Range: 0.8446. Min Range: -0.8446

Max Act: 0.6713. Min Act: -0.0000

Data Index: 1656115 (Python Code)

Max Activating Token Index: 862

Text #11

Max Range: 0.8446. Min Range: -0.8446

Max Act: 0.6076. Min Act: -0.0000

Data Index: 1532470 (Python Code)

Max Activating Token Index: 951

Text #12

Max Range: 0.8446. Min Range: -0.8446

Max Act: 0.6876. Min Act: -0.0000

Data Index: 1451899 (Python Code)

Max Activating Token Index: 458

Text #13

Max Range: 0.8446. Min Range: -0.8446

Max Act: 0.6626. Min Act: -0.0000

Data Index: 916459 (C4 (Web Text))

Max Activating Token Index: 595

Text #14

Max Range: 0.8446. Min Range: -0.8446

Max Act: 0.6767. Min Act: -0.0000

Data Index: 1526341 (Python Code)

Max Activating Token Index: 94

Text #15

Max Range: 0.8446. Min Range: -0.8446

Max Act: 0.6437. Min Act: -0.0000

Data Index: 315770 (C4 (Web Text))

Max Activating Token Index: 293

Text #16

Max Range: 0.8446. Min Range: -0.8446

Max Act: 0.6032. Min Act: -0.0000

Data Index: 1379995 (Python Code)

Max Activating Token Index: 455

Text #17

Max Range: 0.8446. Min Range: -0.8446

Max Act: 0.6321. Min Act: -0.0000

Data Index: 1404822 (Python Code)

Max Activating Token Index: 117

Text #18

Max Range: 0.8446. Min Range: -0.8446

Max Act: 0.5890. Min Act: -0.0000

Data Index: 1365697 (Python Code)

Max Activating Token Index: 900

Text #19

Max Range: 0.8446. Min Range: -0.8446

Max Act: 0.6058. Min Act: -0.0000

Data Index: 1345424 (C4 (Web Text))

Max Activating Token Index: 347