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

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

Neuron 2443 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9426. Min Range: -0.9426

Max Act: 0.9426. Min Act: -0.0000

Data Index: 1637772 (Python Code)

Max Activating Token Index: 735

Text #1

Max Range: 0.9426. Min Range: -0.9426

Max Act: 0.8424. Min Act: -0.0000

Data Index: 1496484 (Python Code)

Max Activating Token Index: 333

Text #2

Max Range: 0.9426. Min Range: -0.9426

Max Act: 0.8001. Min Act: -0.0000

Data Index: 1562201 (Python Code)

Max Activating Token Index: 520

Text #3

Max Range: 0.9426. Min Range: -0.9426

Max Act: 0.8143. Min Act: -0.0000

Data Index: 1494020 (Python Code)

Max Activating Token Index: 462

Text #4

Max Range: 0.9426. Min Range: -0.9426

Max Act: 0.7924. Min Act: -0.0000

Data Index: 1415148 (Python Code)

Max Activating Token Index: 626

Text #5

Max Range: 0.9426. Min Range: -0.9426

Max Act: 0.7031. Min Act: -0.0000

Data Index: 1628462 (Python Code)

Max Activating Token Index: 1019

Text #6

Max Range: 0.9426. Min Range: -0.9426

Max Act: 0.7631. Min Act: -0.0000

Data Index: 1641818 (Python Code)

Max Activating Token Index: 28

Text #7

Max Range: 0.9426. Min Range: -0.9426

Max Act: 0.7942. Min Act: -0.0000

Data Index: 1459238 (Python Code)

Max Activating Token Index: 186

Text #8

Max Range: 0.9426. Min Range: -0.9426

Max Act: 0.6756. Min Act: -0.0000

Data Index: 1391345 (Python Code)

Max Activating Token Index: 890

Text #9

Max Range: 0.9426. Min Range: -0.9426

Max Act: 0.7132. Min Act: -0.0000

Data Index: 1555616 (Python Code)

Max Activating Token Index: 114

Text #10

Max Range: 0.9426. Min Range: -0.9426

Max Act: 0.6879. Min Act: -0.0000

Data Index: 1424782 (Python Code)

Max Activating Token Index: 446

Text #11

Max Range: 0.9426. Min Range: -0.9426

Max Act: 0.6801. Min Act: -0.0000

Data Index: 1435138 (Python Code)

Max Activating Token Index: 558

Text #12

Max Range: 0.9426. Min Range: -0.9426

Max Act: 0.6947. Min Act: -0.0000

Data Index: 1411743 (Python Code)

Max Activating Token Index: 664

Text #13

Max Range: 0.9426. Min Range: -0.9426

Max Act: 0.6967. Min Act: -0.0000

Data Index: 1366864 (Python Code)

Max Activating Token Index: 632

Text #14

Max Range: 0.9426. Min Range: -0.9426

Max Act: 0.6939. Min Act: -0.0000

Data Index: 1400638 (Python Code)

Max Activating Token Index: 598

Text #15

Max Range: 0.9426. Min Range: -0.9426

Max Act: 0.6952. Min Act: -0.0000

Data Index: 1385780 (Python Code)

Max Activating Token Index: 945

Text #16

Max Range: 0.9426. Min Range: -0.9426

Max Act: 0.6480. Min Act: -0.0000

Data Index: 92191 (C4 (Web Text))

Max Activating Token Index: 776

Text #17

Max Range: 0.9426. Min Range: -0.9426

Max Act: 0.6863. Min Act: -0.0000

Data Index: 1418189 (Python Code)

Max Activating Token Index: 447

Text #18

Max Range: 0.9426. Min Range: -0.9426

Max Act: 0.6421. Min Act: -0.0000

Data Index: 1475900 (Python Code)

Max Activating Token Index: 141

Text #19

Max Range: 0.9426. Min Range: -0.9426

Max Act: 0.6862. Min Act: -0.0000

Data Index: 1559013 (Python Code)

Max Activating Token Index: 99