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

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

Neuron 2368 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: 0.9743. Min Range: -0.9743

Max Act: 0.9478. Min Act: -0.0000

Data Index: 1457849 (Python Code)

Max Activating Token Index: 474

Text #1

Max Range: 0.9743. Min Range: -0.9743

Max Act: 0.9725. Min Act: -0.0000

Data Index: 1425923 (Python Code)

Max Activating Token Index: 256

Text #2

Max Range: 0.9743. Min Range: -0.9743

Max Act: 0.9388. Min Act: -0.0000

Data Index: 1559581 (Python Code)

Max Activating Token Index: 430

Text #3

Max Range: 0.9743. Min Range: -0.9743

Max Act: 0.9429. Min Act: -0.0000

Data Index: 1547309 (Python Code)

Max Activating Token Index: 405

Text #4

Max Range: 0.9743. Min Range: -0.9743

Max Act: 0.9743. Min Act: -0.0000

Data Index: 1484247 (Python Code)

Max Activating Token Index: 254

Text #5

Max Range: 0.9743. Min Range: -0.9743

Max Act: 0.8829. Min Act: -0.0000

Data Index: 1587409 (Python Code)

Max Activating Token Index: 548

Text #6

Max Range: 0.9743. Min Range: -0.9743

Max Act: 0.9338. Min Act: -0.0000

Data Index: 1637233 (Python Code)

Max Activating Token Index: 367

Text #7

Max Range: 0.9743. Min Range: -0.9743

Max Act: 0.9345. Min Act: -0.0000

Data Index: 1374157 (Python Code)

Max Activating Token Index: 360

Text #8

Max Range: 0.9743. Min Range: -0.9743

Max Act: 0.8240. Min Act: -0.0000

Data Index: 1440227 (Python Code)

Max Activating Token Index: 289

Text #9

Max Range: 0.9743. Min Range: -0.9743

Max Act: 0.8969. Min Act: -0.0000

Data Index: 1427678 (Python Code)

Max Activating Token Index: 270

Text #10

Max Range: 0.9743. Min Range: -0.9743

Max Act: 0.8412. Min Act: -0.0000

Data Index: 1537720 (Python Code)

Max Activating Token Index: 917

Text #11

Max Range: 0.9743. Min Range: -0.9743

Max Act: 0.8812. Min Act: -0.0000

Data Index: 1572459 (Python Code)

Max Activating Token Index: 608

Text #12

Max Range: 0.9743. Min Range: -0.9743

Max Act: 0.8331. Min Act: -0.0000

Data Index: 1563917 (Python Code)

Max Activating Token Index: 397

Text #13

Max Range: 0.9743. Min Range: -0.9743

Max Act: 0.8959. Min Act: -0.0000

Data Index: 1377341 (Python Code)

Max Activating Token Index: 602

Text #14

Max Range: 0.9743. Min Range: -0.9743

Max Act: 0.7653. Min Act: -0.0000

Data Index: 1380474 (Python Code)

Max Activating Token Index: 261

Text #15

Max Range: 0.9743. Min Range: -0.9743

Max Act: 0.8692. Min Act: -0.0000

Data Index: 1589945 (Python Code)

Max Activating Token Index: 250

Text #16

Max Range: 0.9743. Min Range: -0.9743

Max Act: 0.8634. Min Act: -0.0000

Data Index: 1422323 (Python Code)

Max Activating Token Index: 888

Text #17

Max Range: 0.9743. Min Range: -0.9743

Max Act: 0.8615. Min Act: -0.0000

Data Index: 1426547 (Python Code)

Max Activating Token Index: 818

Text #18

Max Range: 0.9743. Min Range: -0.9743

Max Act: 0.8504. Min Act: -0.0000

Data Index: 1422218 (Python Code)

Max Activating Token Index: 915

Text #19

Max Range: 0.9743. Min Range: -0.9743

Max Act: 0.8198. Min Act: -0.0000

Data Index: 1402769 (Python Code)

Max Activating Token Index: 393