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

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

Neuron 3628 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9927. Min Range: -3.9927

Max Act: 1.8461. Min Act: -0.0000

Data Index: 1132685 (C4 (Web Text))

Max Activating Token Index: 204

Text #1

Max Range: 3.9927. Min Range: -3.9927

Max Act: 3.9927. Min Act: -0.0000

Data Index: 878653 (C4 (Web Text))

Max Activating Token Index: 563

Text #2

Max Range: 3.9927. Min Range: -3.9927

Max Act: 2.1260. Min Act: -0.0000

Data Index: 1467029 (Python Code)

Max Activating Token Index: 309

Text #3

Max Range: 3.9927. Min Range: -3.9927

Max Act: 2.1766. Min Act: -0.0000

Data Index: 1636773 (Python Code)

Max Activating Token Index: 633

Text #4

Max Range: 3.9927. Min Range: -3.9927

Max Act: 2.1113. Min Act: -0.0000

Data Index: 1476403 (Python Code)

Max Activating Token Index: 387

Text #5

Max Range: 3.9927. Min Range: -3.9927

Max Act: 1.8872. Min Act: -0.0000

Data Index: 1438744 (Python Code)

Max Activating Token Index: 720

Text #6

Max Range: 3.9927. Min Range: -3.9927

Max Act: 1.8791. Min Act: -0.0000

Data Index: 1401187 (Python Code)

Max Activating Token Index: 789

Text #7

Max Range: 3.9927. Min Range: -3.9927

Max Act: 1.8665. Min Act: -0.0000

Data Index: 1428478 (Python Code)

Max Activating Token Index: 332

Text #8

Max Range: 3.9927. Min Range: -3.9927

Max Act: 1.8535. Min Act: -0.0000

Data Index: 1519476 (Python Code)

Max Activating Token Index: 431

Text #9

Max Range: 3.9927. Min Range: -3.9927

Max Act: 1.7382. Min Act: -0.0000

Data Index: 1381371 (Python Code)

Max Activating Token Index: 927

Text #10

Max Range: 3.9927. Min Range: -3.9927

Max Act: 1.8070. Min Act: -0.0000

Data Index: 1502575 (Python Code)

Max Activating Token Index: 822

Text #11

Max Range: 3.9927. Min Range: -3.9927

Max Act: 1.7633. Min Act: -0.0000

Data Index: 1501930 (Python Code)

Max Activating Token Index: 970

Text #12

Max Range: 3.9927. Min Range: -3.9927

Max Act: 1.7618. Min Act: -0.0000

Data Index: 1405263 (Python Code)

Max Activating Token Index: 986

Text #13

Max Range: 3.9927. Min Range: -3.9927

Max Act: 1.7464. Min Act: -0.0000

Data Index: 1644846 (Python Code)

Max Activating Token Index: 594

Text #14

Max Range: 3.9927. Min Range: -3.9927

Max Act: 1.8479. Min Act: -0.0000

Data Index: 1565216 (Python Code)

Max Activating Token Index: 702

Text #15

Max Range: 3.9927. Min Range: -3.9927

Max Act: 1.7031. Min Act: -0.0000

Data Index: 1434410 (Python Code)

Max Activating Token Index: 821

Text #16

Max Range: 3.9927. Min Range: -3.9927

Max Act: 1.6115. Min Act: -0.0000

Data Index: 1554613 (Python Code)

Max Activating Token Index: 135

Text #17

Max Range: 3.9927. Min Range: -3.9927

Max Act: 1.6840. Min Act: -0.0000

Data Index: 1432612 (Python Code)

Max Activating Token Index: 880

Text #18

Max Range: 3.9927. Min Range: -3.9927

Max Act: 1.6933. Min Act: -0.0000

Data Index: 101311 (C4 (Web Text))

Max Activating Token Index: 158

Text #19

Max Range: 3.9927. Min Range: -3.9927

Max Act: 1.7949. Min Act: -0.0000

Data Index: 1560328 (Python Code)

Max Activating Token Index: 469