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

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

Neuron 3589 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6865. Min Range: -3.6865

Max Act: 3.6865. Min Act: -0.0000

Data Index: 1426488 (Python Code)

Max Activating Token Index: 259

Text #1

Max Range: 3.6865. Min Range: -3.6865

Max Act: 3.5106. Min Act: -0.0000

Data Index: 1381590 (Python Code)

Max Activating Token Index: 72

Text #2

Max Range: 3.6865. Min Range: -3.6865

Max Act: 3.5718. Min Act: -0.0000

Data Index: 1482620 (Python Code)

Max Activating Token Index: 947

Text #3

Max Range: 3.6865. Min Range: -3.6865

Max Act: 3.3012. Min Act: -0.0000

Data Index: 1401120 (Python Code)

Max Activating Token Index: 641

Text #4

Max Range: 3.6865. Min Range: -3.6865

Max Act: 3.0792. Min Act: -0.0000

Data Index: 1526386 (Python Code)

Max Activating Token Index: 57

Text #5

Max Range: 3.6865. Min Range: -3.6865

Max Act: 3.1918. Min Act: -0.0000

Data Index: 1443381 (Python Code)

Max Activating Token Index: 678

Text #6

Max Range: 3.6865. Min Range: -3.6865

Max Act: 3.0273. Min Act: -0.0000

Data Index: 1445199 (Python Code)

Max Activating Token Index: 56

Text #7

Max Range: 3.6865. Min Range: -3.6865

Max Act: 3.1507. Min Act: -0.0000

Data Index: 1504701 (Python Code)

Max Activating Token Index: 525

Text #8

Max Range: 3.6865. Min Range: -3.6865

Max Act: 2.9970. Min Act: -0.0000

Data Index: 1447239 (Python Code)

Max Activating Token Index: 597

Text #9

Max Range: 3.6865. Min Range: -3.6865

Max Act: 3.2822. Min Act: -0.0000

Data Index: 1612979 (Python Code)

Max Activating Token Index: 103

Text #10

Max Range: 3.6865. Min Range: -3.6865

Max Act: 3.1182. Min Act: -0.0000

Data Index: 1393991 (Python Code)

Max Activating Token Index: 69

Text #11

Max Range: 3.6865. Min Range: -3.6865

Max Act: 3.0829. Min Act: -0.0000

Data Index: 1502238 (Python Code)

Max Activating Token Index: 210

Text #12

Max Range: 3.6865. Min Range: -3.6865

Max Act: 2.9475. Min Act: -0.0000

Data Index: 1604790 (Python Code)

Max Activating Token Index: 195

Text #13

Max Range: 3.6865. Min Range: -3.6865

Max Act: 3.0488. Min Act: -0.0000

Data Index: 1440619 (Python Code)

Max Activating Token Index: 898

Text #14

Max Range: 3.6865. Min Range: -3.6865

Max Act: 3.0608. Min Act: -0.0000

Data Index: 1422641 (Python Code)

Max Activating Token Index: 912

Text #15

Max Range: 3.6865. Min Range: -3.6865

Max Act: 2.9190. Min Act: -0.0000

Data Index: 1611117 (Python Code)

Max Activating Token Index: 366

Text #16

Max Range: 3.6865. Min Range: -3.6865

Max Act: 3.0317. Min Act: -0.0000

Data Index: 1485174 (Python Code)

Max Activating Token Index: 102

Text #17

Max Range: 3.6865. Min Range: -3.6865

Max Act: 3.0093. Min Act: -0.0000

Data Index: 1445442 (Python Code)

Max Activating Token Index: 26

Text #18

Max Range: 3.6865. Min Range: -3.6865

Max Act: 3.0073. Min Act: -0.0000

Data Index: 1642083 (Python Code)

Max Activating Token Index: 876

Text #19

Max Range: 3.6865. Min Range: -3.6865

Max Act: 2.8611. Min Act: -0.0000

Data Index: 1552939 (Python Code)

Max Activating Token Index: 51