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

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

Neuron 2258 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: 1.0461. Min Range: -1.0461

Max Act: 1.0183. Min Act: -0.0000

Data Index: 1591918 (Python Code)

Max Activating Token Index: 909

Text #1

Max Range: 1.0461. Min Range: -1.0461

Max Act: 1.0440. Min Act: -0.0000

Data Index: 1457324 (Python Code)

Max Activating Token Index: 955

Text #2

Max Range: 1.0461. Min Range: -1.0461

Max Act: 1.0461. Min Act: -0.0000

Data Index: 1580069 (Python Code)

Max Activating Token Index: 141

Text #3

Max Range: 1.0461. Min Range: -1.0461

Max Act: 0.9023. Min Act: -0.0000

Data Index: 1361599 (Python Code)

Max Activating Token Index: 546

Text #4

Max Range: 1.0461. Min Range: -1.0461

Max Act: 0.8446. Min Act: -0.0000

Data Index: 1558487 (Python Code)

Max Activating Token Index: 790

Text #5

Max Range: 1.0461. Min Range: -1.0461

Max Act: 0.7974. Min Act: -0.0000

Data Index: 1561967 (Python Code)

Max Activating Token Index: 693

Text #6

Max Range: 1.0461. Min Range: -1.0461

Max Act: 0.8170. Min Act: -0.0000

Data Index: 1655449 (Python Code)

Max Activating Token Index: 88

Text #7

Max Range: 1.0461. Min Range: -1.0461

Max Act: 0.7885. Min Act: -0.0000

Data Index: 1422827 (Python Code)

Max Activating Token Index: 93

Text #8

Max Range: 1.0461. Min Range: -1.0461

Max Act: 0.7698. Min Act: -0.0000

Data Index: 1432605 (Python Code)

Max Activating Token Index: 134

Text #9

Max Range: 1.0461. Min Range: -1.0461

Max Act: 0.7761. Min Act: -0.0000

Data Index: 1381780 (Python Code)

Max Activating Token Index: 955

Text #10

Max Range: 1.0461. Min Range: -1.0461

Max Act: 0.7928. Min Act: -0.0000

Data Index: 1559493 (Python Code)

Max Activating Token Index: 952

Text #11

Max Range: 1.0461. Min Range: -1.0461

Max Act: 0.7431. Min Act: -0.0000

Data Index: 1491634 (Python Code)

Max Activating Token Index: 435

Text #12

Max Range: 1.0461. Min Range: -1.0461

Max Act: 0.6817. Min Act: -0.0000

Data Index: 1538276 (Python Code)

Max Activating Token Index: 220

Text #13

Max Range: 1.0461. Min Range: -1.0461

Max Act: 0.7689. Min Act: -0.0000

Data Index: 1395033 (Python Code)

Max Activating Token Index: 927

Text #14

Max Range: 1.0461. Min Range: -1.0461

Max Act: 0.7239. Min Act: -0.0000

Data Index: 1375362 (Python Code)

Max Activating Token Index: 354

Text #15

Max Range: 1.0461. Min Range: -1.0461

Max Act: 0.7330. Min Act: -0.0000

Data Index: 1558193 (Python Code)

Max Activating Token Index: 801

Text #16

Max Range: 1.0461. Min Range: -1.0461

Max Act: 0.6905. Min Act: -0.0000

Data Index: 1502531 (Python Code)

Max Activating Token Index: 810

Text #17

Max Range: 1.0461. Min Range: -1.0461

Max Act: 0.7118. Min Act: -0.0001

Data Index: 1370731 (Python Code)

Max Activating Token Index: 868

Text #18

Max Range: 1.0461. Min Range: -1.0461

Max Act: 0.7130. Min Act: -0.0000

Data Index: 1423014 (Python Code)

Max Activating Token Index: 116

Text #19

Max Range: 1.0461. Min Range: -1.0461

Max Act: 0.6672. Min Act: -0.0000

Data Index: 1545085 (Python Code)

Max Activating Token Index: 41