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

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

Neuron 4786 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: 0.8637. Min Range: -0.8637

Max Act: 0.8637. Min Act: -0.0000

Data Index: 1441707 (Python Code)

Max Activating Token Index: 102

Text #1

Max Range: 0.8637. Min Range: -0.8637

Max Act: 0.7504. Min Act: -0.0000

Data Index: 1384076 (Python Code)

Max Activating Token Index: 825

Text #2

Max Range: 0.8637. Min Range: -0.8637

Max Act: 0.8066. Min Act: -0.0000

Data Index: 1402461 (Python Code)

Max Activating Token Index: 72

Text #3

Max Range: 0.8637. Min Range: -0.8637

Max Act: 0.8110. Min Act: -0.0000

Data Index: 1531748 (Python Code)

Max Activating Token Index: 241

Text #4

Max Range: 0.8637. Min Range: -0.8637

Max Act: 0.7392. Min Act: -0.0000

Data Index: 1616502 (Python Code)

Max Activating Token Index: 395

Text #5

Max Range: 0.8637. Min Range: -0.8637

Max Act: 0.7513. Min Act: -0.0000

Data Index: 1378927 (Python Code)

Max Activating Token Index: 194

Text #6

Max Range: 0.8637. Min Range: -0.8637

Max Act: 0.7515. Min Act: -0.0000

Data Index: 1408919 (Python Code)

Max Activating Token Index: 706

Text #7

Max Range: 0.8637. Min Range: -0.8637

Max Act: 0.7327. Min Act: -0.0000

Data Index: 1447362 (Python Code)

Max Activating Token Index: 201

Text #8

Max Range: 0.8637. Min Range: -0.8637

Max Act: 0.7015. Min Act: -0.0000

Data Index: 1480852 (Python Code)

Max Activating Token Index: 967

Text #9

Max Range: 0.8637. Min Range: -0.8637

Max Act: 0.6820. Min Act: -0.0000

Data Index: 1430988 (Python Code)

Max Activating Token Index: 868

Text #10

Max Range: 0.8637. Min Range: -0.8637

Max Act: 0.7143. Min Act: -0.0000

Data Index: 1634527 (Python Code)

Max Activating Token Index: 387

Text #11

Max Range: 0.8637. Min Range: -0.8637

Max Act: 0.6940. Min Act: -0.0000

Data Index: 1567868 (Python Code)

Max Activating Token Index: 178

Text #12

Max Range: 0.8637. Min Range: -0.8637

Max Act: 0.7259. Min Act: -0.0000

Data Index: 1526652 (Python Code)

Max Activating Token Index: 539

Text #13

Max Range: 0.8637. Min Range: -0.8637

Max Act: 0.6888. Min Act: -0.0000

Data Index: 1565773 (Python Code)

Max Activating Token Index: 31

Text #14

Max Range: 0.8637. Min Range: -0.8637

Max Act: 0.6489. Min Act: -0.0000

Data Index: 1572373 (Python Code)

Max Activating Token Index: 387

Text #15

Max Range: 0.8637. Min Range: -0.8637

Max Act: 0.6964. Min Act: -0.0000

Data Index: 1464626 (Python Code)

Max Activating Token Index: 705

Text #16

Max Range: 0.8637. Min Range: -0.8637

Max Act: 0.6504. Min Act: -0.0000

Data Index: 1517118 (Python Code)

Max Activating Token Index: 260

Text #17

Max Range: 0.8637. Min Range: -0.8637

Max Act: 0.6533. Min Act: -0.0000

Data Index: 1436873 (Python Code)

Max Activating Token Index: 367

Text #18

Max Range: 0.8637. Min Range: -0.8637

Max Act: 0.6725. Min Act: -0.0000

Data Index: 1627302 (Python Code)

Max Activating Token Index: 320

Text #19

Max Range: 0.8637. Min Range: -0.8637

Max Act: 0.6719. Min Act: -0.0000

Data Index: 1650135 (Python Code)

Max Activating Token Index: 151