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

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

Neuron 507 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8461. Min Range: -0.8461

Max Act: 0.8433. Min Act: -0.0000

Data Index: 1511896 (Python Code)

Max Activating Token Index: 833

Text #1

Max Range: 0.8461. Min Range: -0.8461

Max Act: 0.8461. Min Act: -0.0000

Data Index: 1369756 (Python Code)

Max Activating Token Index: 460

Text #2

Max Range: 0.8461. Min Range: -0.8461

Max Act: 0.8125. Min Act: -0.0000

Data Index: 1624680 (Python Code)

Max Activating Token Index: 535

Text #3

Max Range: 0.8461. Min Range: -0.8461

Max Act: 0.8085. Min Act: -0.0000

Data Index: 1054089 (C4 (Web Text))

Max Activating Token Index: 452

Text #4

Max Range: 0.8461. Min Range: -0.8461

Max Act: 0.8358. Min Act: -0.0000

Data Index: 1526093 (Python Code)

Max Activating Token Index: 782

Text #5

Max Range: 0.8461. Min Range: -0.8461

Max Act: 0.7959. Min Act: -0.0000

Data Index: 1382339 (Python Code)

Max Activating Token Index: 70

Text #6

Max Range: 0.8461. Min Range: -0.8461

Max Act: 0.8214. Min Act: -0.0000

Data Index: 1395015 (Python Code)

Max Activating Token Index: 912

Text #7

Max Range: 0.8461. Min Range: -0.8461

Max Act: 0.8259. Min Act: -0.0000

Data Index: 1560416 (Python Code)

Max Activating Token Index: 1012

Text #8

Max Range: 0.8461. Min Range: -0.8461

Max Act: 0.7497. Min Act: -0.0000

Data Index: 1512825 (Python Code)

Max Activating Token Index: 247

Text #9

Max Range: 0.8461. Min Range: -0.8461

Max Act: 0.7647. Min Act: -0.0000

Data Index: 1377828 (Python Code)

Max Activating Token Index: 248

Text #10

Max Range: 0.8461. Min Range: -0.8461

Max Act: 0.7689. Min Act: -0.0000

Data Index: 1570381 (Python Code)

Max Activating Token Index: 937

Text #11

Max Range: 0.8461. Min Range: -0.8461

Max Act: 0.7431. Min Act: -0.0000

Data Index: 1456082 (Python Code)

Max Activating Token Index: 38

Text #12

Max Range: 0.8461. Min Range: -0.8461

Max Act: 0.7197. Min Act: -0.0000

Data Index: 1477536 (Python Code)

Max Activating Token Index: 437

Text #13

Max Range: 0.8461. Min Range: -0.8461

Max Act: 0.7357. Min Act: -0.0000

Data Index: 1522961 (Python Code)

Max Activating Token Index: 417

Text #14

Max Range: 0.8461. Min Range: -0.8461

Max Act: 0.7505. Min Act: -0.0000

Data Index: 117735 (C4 (Web Text))

Max Activating Token Index: 709

Text #15

Max Range: 0.8461. Min Range: -0.8461

Max Act: 0.7013. Min Act: -0.0000

Data Index: 1635423 (Python Code)

Max Activating Token Index: 847

Text #16

Max Range: 0.8461. Min Range: -0.8461

Max Act: 0.6567. Min Act: -0.0000

Data Index: 1470039 (Python Code)

Max Activating Token Index: 977

Text #17

Max Range: 0.8461. Min Range: -0.8461

Max Act: 0.7235. Min Act: -0.0000

Data Index: 1574671 (Python Code)

Max Activating Token Index: 774

Text #18

Max Range: 0.8461. Min Range: -0.8461

Max Act: 0.6701. Min Act: -0.0000

Data Index: 1442948 (Python Code)

Max Activating Token Index: 587

Text #19

Max Range: 0.8461. Min Range: -0.8461

Max Act: 0.6915. Min Act: -0.0000

Data Index: 1642695 (Python Code)

Max Activating Token Index: 71