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

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

Neuron 1948 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: 0.3719. Min Range: -0.3719

Max Act: 0.3719. Min Act: -0.0000

Data Index: 1422095 (Python Code)

Max Activating Token Index: 398

Text #1

Max Range: 0.3719. Min Range: -0.3719

Max Act: 0.3576. Min Act: -0.0000

Data Index: 1395328 (Python Code)

Max Activating Token Index: 614

Text #2

Max Range: 0.3719. Min Range: -0.3719

Max Act: 0.3191. Min Act: -0.0000

Data Index: 1490289 (Python Code)

Max Activating Token Index: 54

Text #3

Max Range: 0.3719. Min Range: -0.3719

Max Act: 0.3223. Min Act: -0.0000

Data Index: 1263733 (C4 (Web Text))

Max Activating Token Index: 895

Text #4

Max Range: 0.3719. Min Range: -0.3719

Max Act: 0.2910. Min Act: -0.0000

Data Index: 1389129 (Python Code)

Max Activating Token Index: 663

Text #5

Max Range: 0.3719. Min Range: -0.3719

Max Act: 0.2814. Min Act: -0.0000

Data Index: 299024 (C4 (Web Text))

Max Activating Token Index: 168

Text #6

Max Range: 0.3719. Min Range: -0.3719

Max Act: 0.3029. Min Act: -0.0000

Data Index: 1319618 (C4 (Web Text))

Max Activating Token Index: 214

Text #7

Max Range: 0.3719. Min Range: -0.3719

Max Act: 0.2630. Min Act: -0.0000

Data Index: 610503 (C4 (Web Text))

Max Activating Token Index: 347

Text #8

Max Range: 0.3719. Min Range: -0.3719

Max Act: 0.2665. Min Act: -0.0000

Data Index: 1349812 (C4 (Web Text))

Max Activating Token Index: 508

Text #9

Max Range: 0.3719. Min Range: -0.3719

Max Act: 0.2622. Min Act: -0.0000

Data Index: 1329938 (C4 (Web Text))

Max Activating Token Index: 125

Text #10

Max Range: 0.3719. Min Range: -0.3719

Max Act: 0.2595. Min Act: -0.0000

Data Index: 1461247 (Python Code)

Max Activating Token Index: 886

Text #11

Max Range: 0.3719. Min Range: -0.3719

Max Act: 0.2674. Min Act: -0.0000

Data Index: 1360531 (Python Code)

Max Activating Token Index: 545

Text #12

Max Range: 0.3719. Min Range: -0.3719

Max Act: 0.2536. Min Act: -0.0000

Data Index: 1421914 (Python Code)

Max Activating Token Index: 298

Text #13

Max Range: 0.3719. Min Range: -0.3719

Max Act: 0.2545. Min Act: -0.0000

Data Index: 1587241 (Python Code)

Max Activating Token Index: 269

Text #14

Max Range: 0.3719. Min Range: -0.3719

Max Act: 0.2502. Min Act: -0.0000

Data Index: 1647857 (Python Code)

Max Activating Token Index: 495

Text #15

Max Range: 0.3719. Min Range: -0.3719

Max Act: 0.2448. Min Act: -0.0000

Data Index: 1509147 (Python Code)

Max Activating Token Index: 525

Text #16

Max Range: 0.3719. Min Range: -0.3719

Max Act: 0.2454. Min Act: -0.0000

Data Index: 1369610 (Python Code)

Max Activating Token Index: 649

Text #17

Max Range: 0.3719. Min Range: -0.3719

Max Act: 0.2697. Min Act: -0.0000

Data Index: 1571055 (Python Code)

Max Activating Token Index: 761

Text #18

Max Range: 0.3719. Min Range: -0.3719

Max Act: 0.2355. Min Act: -0.0000

Data Index: 1610409 (Python Code)

Max Activating Token Index: 250

Text #19

Max Range: 0.3719. Min Range: -0.3719

Max Act: 0.2603. Min Act: -0.0000

Data Index: 1547031 (Python Code)

Max Activating Token Index: 882