Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4020 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.8913. Min Range: -0.8913

Max Act: 0.8913. Min Act: -0.0000

Data Index: 1291083 (C4 (Web Text))

Max Activating Token Index: 405

Text #1

Max Range: 0.8913. Min Range: -0.8913

Max Act: 0.7941. Min Act: -0.0000

Data Index: 322798 (C4 (Web Text))

Max Activating Token Index: 353

Text #2

Max Range: 0.8913. Min Range: -0.8913

Max Act: 0.7890. Min Act: -0.0000

Data Index: 1427020 (Python Code)

Max Activating Token Index: 776

Text #3

Max Range: 0.8913. Min Range: -0.8913

Max Act: 0.7945. Min Act: -0.0000

Data Index: 1405557 (Python Code)

Max Activating Token Index: 949

Text #4

Max Range: 0.8913. Min Range: -0.8913

Max Act: 0.7608. Min Act: -0.0000

Data Index: 1522502 (Python Code)

Max Activating Token Index: 897

Text #5

Max Range: 0.8913. Min Range: -0.8913

Max Act: 0.7675. Min Act: -0.0000

Data Index: 1431063 (Python Code)

Max Activating Token Index: 732

Text #6

Max Range: 0.8913. Min Range: -0.8913

Max Act: 0.7430. Min Act: -0.0000

Data Index: 1406244 (Python Code)

Max Activating Token Index: 506

Text #7

Max Range: 0.8913. Min Range: -0.8913

Max Act: 0.7324. Min Act: -0.0000

Data Index: 1370588 (Python Code)

Max Activating Token Index: 682

Text #8

Max Range: 0.8913. Min Range: -0.8913

Max Act: 0.7396. Min Act: -0.0000

Data Index: 1422928 (Python Code)

Max Activating Token Index: 536

Text #9

Max Range: 0.8913. Min Range: -0.8913

Max Act: 0.7270. Min Act: -0.0000

Data Index: 1644721 (Python Code)

Max Activating Token Index: 562

Text #10

Max Range: 0.8913. Min Range: -0.8913

Max Act: 0.7031. Min Act: -0.0000

Data Index: 1502788 (Python Code)

Max Activating Token Index: 738

Text #11

Max Range: 0.8913. Min Range: -0.8913

Max Act: 0.7571. Min Act: -0.0000

Data Index: 1549609 (Python Code)

Max Activating Token Index: 766

Text #12

Max Range: 0.8913. Min Range: -0.8913

Max Act: 0.7474. Min Act: -0.0000

Data Index: 1611485 (Python Code)

Max Activating Token Index: 748

Text #13

Max Range: 0.8913. Min Range: -0.8913

Max Act: 0.7270. Min Act: -0.0000

Data Index: 1573224 (Python Code)

Max Activating Token Index: 114

Text #14

Max Range: 0.8913. Min Range: -0.8913

Max Act: 0.7464. Min Act: -0.0000

Data Index: 1369026 (Python Code)

Max Activating Token Index: 902

Text #15

Max Range: 0.8913. Min Range: -0.8913

Max Act: 0.6971. Min Act: -0.0000

Data Index: 1598191 (Python Code)

Max Activating Token Index: 705

Text #16

Max Range: 0.8913. Min Range: -0.8913

Max Act: 0.7461. Min Act: -0.0000

Data Index: 1646028 (Python Code)

Max Activating Token Index: 882

Text #17

Max Range: 0.8913. Min Range: -0.8913

Max Act: 0.6940. Min Act: -0.0000

Data Index: 1592296 (Python Code)

Max Activating Token Index: 748

Text #18

Max Range: 0.8913. Min Range: -0.8913

Max Act: 0.6840. Min Act: -0.0000

Data Index: 492566 (C4 (Web Text))

Max Activating Token Index: 788

Text #19

Max Range: 0.8913. Min Range: -0.8913

Max Act: 0.7025. Min Act: -0.0000

Data Index: 1125002 (C4 (Web Text))

Max Activating Token Index: 727