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

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

Neuron 650 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6978. Min Range: -3.6978

Max Act: 3.6978. Min Act: -0.0000

Data Index: 996658 (C4 (Web Text))

Max Activating Token Index: 27

Text #1

Max Range: 3.6978. Min Range: -3.6978

Max Act: 3.5431. Min Act: -0.0000

Data Index: 1443783 (Python Code)

Max Activating Token Index: 792

Text #2

Max Range: 3.6978. Min Range: -3.6978

Max Act: 3.2780. Min Act: -0.0000

Data Index: 1382699 (Python Code)

Max Activating Token Index: 343

Text #3

Max Range: 3.6978. Min Range: -3.6978

Max Act: 3.3656. Min Act: -0.0000

Data Index: 1488199 (Python Code)

Max Activating Token Index: 609

Text #4

Max Range: 3.6978. Min Range: -3.6978

Max Act: 3.1633. Min Act: -0.0000

Data Index: 1633515 (Python Code)

Max Activating Token Index: 156

Text #5

Max Range: 3.6978. Min Range: -3.6978

Max Act: 3.2441. Min Act: -0.0000

Data Index: 1125967 (C4 (Web Text))

Max Activating Token Index: 589

Text #6

Max Range: 3.6978. Min Range: -3.6978

Max Act: 3.4037. Min Act: -0.0000

Data Index: 480815 (C4 (Web Text))

Max Activating Token Index: 394

Text #7

Max Range: 3.6978. Min Range: -3.6978

Max Act: 3.2390. Min Act: -0.0000

Data Index: 1546326 (Python Code)

Max Activating Token Index: 616

Text #8

Max Range: 3.6978. Min Range: -3.6978

Max Act: 3.1938. Min Act: -0.0000

Data Index: 1550451 (Python Code)

Max Activating Token Index: 981

Text #9

Max Range: 3.6978. Min Range: -3.6978

Max Act: 3.1569. Min Act: -0.0000

Data Index: 1361280 (Python Code)

Max Activating Token Index: 392

Text #10

Max Range: 3.6978. Min Range: -3.6978

Max Act: 3.1172. Min Act: -0.0000

Data Index: 1583903 (Python Code)

Max Activating Token Index: 217

Text #11

Max Range: 3.6978. Min Range: -3.6978

Max Act: 3.1371. Min Act: -0.0000

Data Index: 1500328 (Python Code)

Max Activating Token Index: 56

Text #12

Max Range: 3.6978. Min Range: -3.6978

Max Act: 3.2456. Min Act: -0.0000

Data Index: 1461594 (Python Code)

Max Activating Token Index: 147

Text #13

Max Range: 3.6978. Min Range: -3.6978

Max Act: 3.0783. Min Act: -0.0000

Data Index: 1473819 (Python Code)

Max Activating Token Index: 584

Text #14

Max Range: 3.6978. Min Range: -3.6978

Max Act: 2.9381. Min Act: -0.0000

Data Index: 1559367 (Python Code)

Max Activating Token Index: 406

Text #15

Max Range: 3.6978. Min Range: -3.6978

Max Act: 3.0389. Min Act: -0.0000

Data Index: 1650214 (Python Code)

Max Activating Token Index: 631

Text #16

Max Range: 3.6978. Min Range: -3.6978

Max Act: 3.1888. Min Act: -0.0000

Data Index: 1650572 (Python Code)

Max Activating Token Index: 646

Text #17

Max Range: 3.6978. Min Range: -3.6978

Max Act: 3.1484. Min Act: -0.0000

Data Index: 1410279 (Python Code)

Max Activating Token Index: 1019

Text #18

Max Range: 3.6978. Min Range: -3.6978

Max Act: 3.1594. Min Act: -0.0000

Data Index: 1364217 (Python Code)

Max Activating Token Index: 612

Text #19

Max Range: 3.6978. Min Range: -3.6978

Max Act: 3.0315. Min Act: -0.0000

Data Index: 1453106 (Python Code)

Max Activating Token Index: 883