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

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

Neuron 1115 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9835. Min Range: -0.9835

Max Act: 0.9467. Min Act: -0.0000

Data Index: 1477595 (Python Code)

Max Activating Token Index: 879

Text #1

Max Range: 0.9835. Min Range: -0.9835

Max Act: 0.9820. Min Act: -0.0000

Data Index: 1472917 (Python Code)

Max Activating Token Index: 488

Text #2

Max Range: 0.9835. Min Range: -0.9835

Max Act: 0.9167. Min Act: -0.0000

Data Index: 1435975 (Python Code)

Max Activating Token Index: 231

Text #3

Max Range: 0.9835. Min Range: -0.9835

Max Act: 0.9291. Min Act: -0.0000

Data Index: 1601265 (Python Code)

Max Activating Token Index: 155

Text #4

Max Range: 0.9835. Min Range: -0.9835

Max Act: 0.9835. Min Act: -0.0000

Data Index: 1575826 (Python Code)

Max Activating Token Index: 936

Text #5

Max Range: 0.9835. Min Range: -0.9835

Max Act: 0.9412. Min Act: -0.0000

Data Index: 1521379 (Python Code)

Max Activating Token Index: 25

Text #6

Max Range: 0.9835. Min Range: -0.9835

Max Act: 0.8414. Min Act: -0.0000

Data Index: 1596123 (Python Code)

Max Activating Token Index: 544

Text #7

Max Range: 0.9835. Min Range: -0.9835

Max Act: 0.9123. Min Act: -0.0000

Data Index: 1602599 (Python Code)

Max Activating Token Index: 417

Text #8

Max Range: 0.9835. Min Range: -0.9835

Max Act: 0.8873. Min Act: -0.0000

Data Index: 1507399 (Python Code)

Max Activating Token Index: 62

Text #9

Max Range: 0.9835. Min Range: -0.9835

Max Act: 0.9102. Min Act: -0.0000

Data Index: 1496857 (Python Code)

Max Activating Token Index: 578

Text #10

Max Range: 0.9835. Min Range: -0.9835

Max Act: 0.8931. Min Act: -0.0000

Data Index: 1619603 (Python Code)

Max Activating Token Index: 8

Text #11

Max Range: 0.9835. Min Range: -0.9835

Max Act: 0.9436. Min Act: -0.0000

Data Index: 1535685 (Python Code)

Max Activating Token Index: 165

Text #12

Max Range: 0.9835. Min Range: -0.9835

Max Act: 0.8864. Min Act: -0.0000

Data Index: 1505054 (Python Code)

Max Activating Token Index: 545

Text #13

Max Range: 0.9835. Min Range: -0.9835

Max Act: 0.8271. Min Act: -0.0000

Data Index: 1518254 (Python Code)

Max Activating Token Index: 484

Text #14

Max Range: 0.9835. Min Range: -0.9835

Max Act: 0.8816. Min Act: -0.0000

Data Index: 1584589 (Python Code)

Max Activating Token Index: 222

Text #15

Max Range: 0.9835. Min Range: -0.9835

Max Act: 0.8807. Min Act: -0.0000

Data Index: 1587597 (Python Code)

Max Activating Token Index: 773

Text #16

Max Range: 0.9835. Min Range: -0.9835

Max Act: 0.8421. Min Act: -0.0000

Data Index: 1594186 (Python Code)

Max Activating Token Index: 942

Text #17

Max Range: 0.9835. Min Range: -0.9835

Max Act: 0.8960. Min Act: -0.0000

Data Index: 1455258 (Python Code)

Max Activating Token Index: 81

Text #18

Max Range: 0.9835. Min Range: -0.9835

Max Act: 0.7800. Min Act: -0.0000

Data Index: 1407442 (Python Code)

Max Activating Token Index: 885

Text #19

Max Range: 0.9835. Min Range: -0.9835

Max Act: 0.9763. Min Act: -0.0000

Data Index: 1645288 (Python Code)

Max Activating Token Index: 835