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

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

Neuron 2442 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: 0.0838. Min Range: -0.0838

Max Act: 0.0838. Min Act: -0.0000

Data Index: 256906 (C4 (Web Text))

Max Activating Token Index: 572

Text #1

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0728. Min Act: -0.0000

Data Index: 1548927 (Python Code)

Max Activating Token Index: 612

Text #2

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0658. Min Act: -0.0000

Data Index: 1627583 (Python Code)

Max Activating Token Index: 535

Text #3

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0580. Min Act: -0.0000

Data Index: 1604969 (Python Code)

Max Activating Token Index: 591

Text #4

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0576. Min Act: -0.0000

Data Index: 654723 (C4 (Web Text))

Max Activating Token Index: 490

Text #5

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0581. Min Act: -0.0000

Data Index: 1395118 (Python Code)

Max Activating Token Index: 383

Text #6

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0506. Min Act: -0.0000

Data Index: 113109 (C4 (Web Text))

Max Activating Token Index: 987

Text #7

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0519. Min Act: -0.0000

Data Index: 1624645 (Python Code)

Max Activating Token Index: 524

Text #8

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0458. Min Act: -0.0000

Data Index: 1416178 (Python Code)

Max Activating Token Index: 551

Text #9

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0488. Min Act: -0.0000

Data Index: 822357 (C4 (Web Text))

Max Activating Token Index: 52

Text #10

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0434. Min Act: -0.0000

Data Index: 1320885 (C4 (Web Text))

Max Activating Token Index: 637

Text #11

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0434. Min Act: -0.0000

Data Index: 1480540 (Python Code)

Max Activating Token Index: 367

Text #12

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0460. Min Act: -0.0000

Data Index: 1078121 (C4 (Web Text))

Max Activating Token Index: 987

Text #13

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0418. Min Act: -0.0000

Data Index: 1515819 (Python Code)

Max Activating Token Index: 613

Text #14

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0452. Min Act: -0.0000

Data Index: 617439 (C4 (Web Text))

Max Activating Token Index: 1002

Text #15

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0474. Min Act: -0.0000

Data Index: 1239400 (C4 (Web Text))

Max Activating Token Index: 997

Text #16

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0450. Min Act: -0.0000

Data Index: 441108 (C4 (Web Text))

Max Activating Token Index: 552

Text #17

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0453. Min Act: -0.0000

Data Index: 1644826 (Python Code)

Max Activating Token Index: 819

Text #18

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0437. Min Act: -0.0000

Data Index: 696977 (C4 (Web Text))

Max Activating Token Index: 341

Text #19

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0458. Min Act: -0.0000

Data Index: 1471507 (Python Code)

Max Activating Token Index: 995