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

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

Neuron 2428 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: 1.9745. Min Range: -1.9745

Max Act: 1.9745. Min Act: -0.0000

Data Index: 721031 (C4 (Web Text))

Max Activating Token Index: 771

Text #1

Max Range: 1.9745. Min Range: -1.9745

Max Act: 1.6445. Min Act: -0.0000

Data Index: 771170 (C4 (Web Text))

Max Activating Token Index: 25

Text #2

Max Range: 1.9745. Min Range: -1.9745

Max Act: 1.1470. Min Act: -0.0000

Data Index: 1402870 (Python Code)

Max Activating Token Index: 322

Text #3

Max Range: 1.9745. Min Range: -1.9745

Max Act: 1.1440. Min Act: -0.0000

Data Index: 1624418 (Python Code)

Max Activating Token Index: 857

Text #4

Max Range: 1.9745. Min Range: -1.9745

Max Act: 1.1090. Min Act: -0.0000

Data Index: 1541572 (Python Code)

Max Activating Token Index: 248

Text #5

Max Range: 1.9745. Min Range: -1.9745

Max Act: 0.9504. Min Act: -0.0000

Data Index: 1381899 (Python Code)

Max Activating Token Index: 622

Text #6

Max Range: 1.9745. Min Range: -1.9745

Max Act: 0.8956. Min Act: -0.0000

Data Index: 1653264 (Python Code)

Max Activating Token Index: 1012

Text #7

Max Range: 1.9745. Min Range: -1.9745

Max Act: 0.8879. Min Act: -0.0000

Data Index: 1643676 (Python Code)

Max Activating Token Index: 912

Text #8

Max Range: 1.9745. Min Range: -1.9745

Max Act: 0.9047. Min Act: -0.0000

Data Index: 1377351 (Python Code)

Max Activating Token Index: 86

Text #9

Max Range: 1.9745. Min Range: -1.9745

Max Act: 0.8763. Min Act: -0.0000

Data Index: 1417838 (Python Code)

Max Activating Token Index: 294

Text #10

Max Range: 1.9745. Min Range: -1.9745

Max Act: 0.8688. Min Act: -0.0000

Data Index: 1451848 (Python Code)

Max Activating Token Index: 871

Text #11

Max Range: 1.9745. Min Range: -1.9745

Max Act: 0.8342. Min Act: -0.0000

Data Index: 1570195 (Python Code)

Max Activating Token Index: 65

Text #12

Max Range: 1.9745. Min Range: -1.9745

Max Act: 0.8442. Min Act: -0.0000

Data Index: 1259171 (C4 (Web Text))

Max Activating Token Index: 384

Text #13

Max Range: 1.9745. Min Range: -1.9745

Max Act: 0.7902. Min Act: -0.0000

Data Index: 1523298 (Python Code)

Max Activating Token Index: 100

Text #14

Max Range: 1.9745. Min Range: -1.9745

Max Act: 0.7301. Min Act: -0.0000

Data Index: 1642535 (Python Code)

Max Activating Token Index: 537

Text #15

Max Range: 1.9745. Min Range: -1.9745

Max Act: 0.7498. Min Act: -0.0000

Data Index: 1456965 (Python Code)

Max Activating Token Index: 99

Text #16

Max Range: 1.9745. Min Range: -1.9745

Max Act: 0.7566. Min Act: -0.0000

Data Index: 1459766 (Python Code)

Max Activating Token Index: 435

Text #17

Max Range: 1.9745. Min Range: -1.9745

Max Act: 0.7772. Min Act: -0.0000

Data Index: 1438575 (Python Code)

Max Activating Token Index: 270

Text #18

Max Range: 1.9745. Min Range: -1.9745

Max Act: 0.7078. Min Act: -0.0000

Data Index: 1396720 (Python Code)

Max Activating Token Index: 822

Text #19

Max Range: 1.9745. Min Range: -1.9745

Max Act: 0.7081. Min Act: -0.0000

Data Index: 1492533 (Python Code)

Max Activating Token Index: 788