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

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

Neuron 3353 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: 0.8927. Min Range: -0.8927

Max Act: 0.7863. Min Act: -0.0000

Data Index: 1418079 (Python Code)

Max Activating Token Index: 680

Text #1

Max Range: 0.8927. Min Range: -0.8927

Max Act: 0.8927. Min Act: -0.0000

Data Index: 1370127 (Python Code)

Max Activating Token Index: 190

Text #2

Max Range: 0.8927. Min Range: -0.8927

Max Act: 0.5899. Min Act: -0.0000

Data Index: 1549893 (Python Code)

Max Activating Token Index: 884

Text #3

Max Range: 0.8927. Min Range: -0.8927

Max Act: 0.7059. Min Act: -0.0000

Data Index: 1499688 (Python Code)

Max Activating Token Index: 603

Text #4

Max Range: 0.8927. Min Range: -0.8927

Max Act: 0.6559. Min Act: -0.0000

Data Index: 1416025 (Python Code)

Max Activating Token Index: 713

Text #5

Max Range: 0.8927. Min Range: -0.8927

Max Act: 0.6510. Min Act: -0.0000

Data Index: 1455198 (Python Code)

Max Activating Token Index: 83

Text #6

Max Range: 0.8927. Min Range: -0.8927

Max Act: 0.5989. Min Act: -0.0000

Data Index: 1512305 (Python Code)

Max Activating Token Index: 551

Text #7

Max Range: 0.8927. Min Range: -0.8927

Max Act: 0.5849. Min Act: -0.0000

Data Index: 1534493 (Python Code)

Max Activating Token Index: 961

Text #8

Max Range: 0.8927. Min Range: -0.8927

Max Act: 0.5454. Min Act: -0.0000

Data Index: 1591716 (Python Code)

Max Activating Token Index: 458

Text #9

Max Range: 0.8927. Min Range: -0.8927

Max Act: 0.5519. Min Act: -0.0000

Data Index: 1655729 (Python Code)

Max Activating Token Index: 293

Text #10

Max Range: 0.8927. Min Range: -0.8927

Max Act: 0.5474. Min Act: -0.0000

Data Index: 1364289 (Python Code)

Max Activating Token Index: 369

Text #11

Max Range: 0.8927. Min Range: -0.8927

Max Act: 0.5290. Min Act: -0.0000

Data Index: 1565261 (Python Code)

Max Activating Token Index: 719

Text #12

Max Range: 0.8927. Min Range: -0.8927

Max Act: 0.5664. Min Act: -0.0000

Data Index: 1639445 (Python Code)

Max Activating Token Index: 233

Text #13

Max Range: 0.8927. Min Range: -0.8927

Max Act: 0.5336. Min Act: -0.0000

Data Index: 1437041 (Python Code)

Max Activating Token Index: 466

Text #14

Max Range: 0.8927. Min Range: -0.8927

Max Act: 0.5331. Min Act: -0.0000

Data Index: 1443445 (Python Code)

Max Activating Token Index: 285

Text #15

Max Range: 0.8927. Min Range: -0.8927

Max Act: 0.5245. Min Act: -0.0000

Data Index: 1471330 (Python Code)

Max Activating Token Index: 302

Text #16

Max Range: 0.8927. Min Range: -0.8927

Max Act: 0.5773. Min Act: -0.0000

Data Index: 1650368 (Python Code)

Max Activating Token Index: 793

Text #17

Max Range: 0.8927. Min Range: -0.8927

Max Act: 0.5192. Min Act: -0.0000

Data Index: 1493341 (Python Code)

Max Activating Token Index: 229

Text #18

Max Range: 0.8927. Min Range: -0.8927

Max Act: 0.4864. Min Act: -0.0000

Data Index: 1642511 (Python Code)

Max Activating Token Index: 232

Text #19

Max Range: 0.8927. Min Range: -0.8927

Max Act: 0.5008. Min Act: -0.0000

Data Index: 1393343 (Python Code)

Max Activating Token Index: 650