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

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

Neuron 5641 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.9461. Min Range: -7.9461

Max Act: 7.9461. Min Act: -0.0000

Data Index: 1373481 (Python Code)

Max Activating Token Index: 675

Text #1

Max Range: 7.9461. Min Range: -7.9461

Max Act: 7.6849. Min Act: -0.0000

Data Index: 1469511 (Python Code)

Max Activating Token Index: 241

Text #2

Max Range: 7.9461. Min Range: -7.9461

Max Act: 7.7602. Min Act: -0.0000

Data Index: 1392343 (Python Code)

Max Activating Token Index: 295

Text #3

Max Range: 7.9461. Min Range: -7.9461

Max Act: 7.2623. Min Act: -0.0000

Data Index: 1457460 (Python Code)

Max Activating Token Index: 186

Text #4

Max Range: 7.9461. Min Range: -7.9461

Max Act: 6.9775. Min Act: -0.0000

Data Index: 1573738 (Python Code)

Max Activating Token Index: 140

Text #5

Max Range: 7.9461. Min Range: -7.9461

Max Act: 6.7544. Min Act: -0.0000

Data Index: 1394094 (Python Code)

Max Activating Token Index: 293

Text #6

Max Range: 7.9461. Min Range: -7.9461

Max Act: 6.6753. Min Act: -0.0000

Data Index: 1592000 (Python Code)

Max Activating Token Index: 311

Text #7

Max Range: 7.9461. Min Range: -7.9461

Max Act: 6.8433. Min Act: -0.0000

Data Index: 1380460 (Python Code)

Max Activating Token Index: 20

Text #8

Max Range: 7.9461. Min Range: -7.9461

Max Act: 6.9732. Min Act: -0.0000

Data Index: 1469804 (Python Code)

Max Activating Token Index: 539

Text #9

Max Range: 7.9461. Min Range: -7.9461

Max Act: 6.5711. Min Act: -0.0000

Data Index: 1490078 (Python Code)

Max Activating Token Index: 278

Text #10

Max Range: 7.9461. Min Range: -7.9461

Max Act: 6.6067. Min Act: -0.0000

Data Index: 1407531 (Python Code)

Max Activating Token Index: 222

Text #11

Max Range: 7.9461. Min Range: -7.9461

Max Act: 6.5937. Min Act: -0.0000

Data Index: 1371115 (Python Code)

Max Activating Token Index: 838

Text #12

Max Range: 7.9461. Min Range: -7.9461

Max Act: 6.3850. Min Act: -0.0000

Data Index: 1506131 (Python Code)

Max Activating Token Index: 413

Text #13

Max Range: 7.9461. Min Range: -7.9461

Max Act: 6.5571. Min Act: -0.0000

Data Index: 1480979 (Python Code)

Max Activating Token Index: 558

Text #14

Max Range: 7.9461. Min Range: -7.9461

Max Act: 6.5884. Min Act: -0.0000

Data Index: 1409475 (Python Code)

Max Activating Token Index: 200

Text #15

Max Range: 7.9461. Min Range: -7.9461

Max Act: 6.3477. Min Act: -0.0000

Data Index: 1441568 (Python Code)

Max Activating Token Index: 851

Text #16

Max Range: 7.9461. Min Range: -7.9461

Max Act: 6.2875. Min Act: -0.0000

Data Index: 1410185 (Python Code)

Max Activating Token Index: 266

Text #17

Max Range: 7.9461. Min Range: -7.9461

Max Act: 6.0925. Min Act: -0.0000

Data Index: 1493929 (Python Code)

Max Activating Token Index: 26

Text #18

Max Range: 7.9461. Min Range: -7.9461

Max Act: 6.4461. Min Act: -0.0000

Data Index: 1492255 (Python Code)

Max Activating Token Index: 529

Text #19

Max Range: 7.9461. Min Range: -7.9461

Max Act: 6.4300. Min Act: -0.0000

Data Index: 1636325 (Python Code)

Max Activating Token Index: 672