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

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

Neuron 3296 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6631. Min Range: -0.6631

Max Act: 0.6290. Min Act: -0.0000

Data Index: 1432465 (Python Code)

Max Activating Token Index: 386

Text #1

Max Range: 0.6631. Min Range: -0.6631

Max Act: 0.6260. Min Act: -0.0000

Data Index: 1595966 (Python Code)

Max Activating Token Index: 358

Text #2

Max Range: 0.6631. Min Range: -0.6631

Max Act: 0.6629. Min Act: -0.0000

Data Index: 607069 (C4 (Web Text))

Max Activating Token Index: 239

Text #3

Max Range: 0.6631. Min Range: -0.6631

Max Act: 0.6631. Min Act: -0.0000

Data Index: 148829 (C4 (Web Text))

Max Activating Token Index: 231

Text #4

Max Range: 0.6631. Min Range: -0.6631

Max Act: 0.5747. Min Act: -0.0000

Data Index: 1559516 (Python Code)

Max Activating Token Index: 835

Text #5

Max Range: 0.6631. Min Range: -0.6631

Max Act: 0.5498. Min Act: -0.0000

Data Index: 504533 (C4 (Web Text))

Max Activating Token Index: 601

Text #6

Max Range: 0.6631. Min Range: -0.6631

Max Act: 0.5661. Min Act: -0.0000

Data Index: 1556882 (Python Code)

Max Activating Token Index: 100

Text #7

Max Range: 0.6631. Min Range: -0.6631

Max Act: 0.5663. Min Act: -0.0000

Data Index: 577950 (C4 (Web Text))

Max Activating Token Index: 777

Text #8

Max Range: 0.6631. Min Range: -0.6631

Max Act: 0.5623. Min Act: -0.0000

Data Index: 378436 (C4 (Web Text))

Max Activating Token Index: 452

Text #9

Max Range: 0.6631. Min Range: -0.6631

Max Act: 0.5184. Min Act: -0.0000

Data Index: 1397117 (Python Code)

Max Activating Token Index: 826

Text #10

Max Range: 0.6631. Min Range: -0.6631

Max Act: 0.6073. Min Act: -0.0000

Data Index: 1552234 (Python Code)

Max Activating Token Index: 338

Text #11

Max Range: 0.6631. Min Range: -0.6631

Max Act: 0.5212. Min Act: -0.0000

Data Index: 1602459 (Python Code)

Max Activating Token Index: 680

Text #12

Max Range: 0.6631. Min Range: -0.6631

Max Act: 0.5132. Min Act: -0.0000

Data Index: 1570670 (Python Code)

Max Activating Token Index: 397

Text #13

Max Range: 0.6631. Min Range: -0.6631

Max Act: 0.5276. Min Act: -0.0000

Data Index: 1602924 (Python Code)

Max Activating Token Index: 174

Text #14

Max Range: 0.6631. Min Range: -0.6631

Max Act: 0.5733. Min Act: -0.0000

Data Index: 861012 (C4 (Web Text))

Max Activating Token Index: 1014

Text #15

Max Range: 0.6631. Min Range: -0.6631

Max Act: 0.4992. Min Act: -0.0000

Data Index: 1635250 (Python Code)

Max Activating Token Index: 523

Text #16

Max Range: 0.6631. Min Range: -0.6631

Max Act: 0.5104. Min Act: -0.0000

Data Index: 1365271 (Python Code)

Max Activating Token Index: 145

Text #17

Max Range: 0.6631. Min Range: -0.6631

Max Act: 0.5052. Min Act: -0.0000

Data Index: 1388478 (Python Code)

Max Activating Token Index: 915

Text #18

Max Range: 0.6631. Min Range: -0.6631

Max Act: 0.5046. Min Act: -0.0000

Data Index: 1487414 (Python Code)

Max Activating Token Index: 550

Text #19

Max Range: 0.6631. Min Range: -0.6631

Max Act: 0.4424. Min Act: -0.0000

Data Index: 665800 (C4 (Web Text))

Max Activating Token Index: 328