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

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

Neuron 5408 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0691. Min Range: -3.0691

Max Act: 2.9886. Min Act: -0.0000

Data Index: 1378710 (Python Code)

Max Activating Token Index: 843

Text #1

Max Range: 3.0691. Min Range: -3.0691

Max Act: 2.9571. Min Act: -0.0000

Data Index: 1612379 (Python Code)

Max Activating Token Index: 715

Text #2

Max Range: 3.0691. Min Range: -3.0691

Max Act: 3.0691. Min Act: -0.0000

Data Index: 1434282 (Python Code)

Max Activating Token Index: 32

Text #3

Max Range: 3.0691. Min Range: -3.0691

Max Act: 2.6569. Min Act: -0.0000

Data Index: 1432205 (Python Code)

Max Activating Token Index: 301

Text #4

Max Range: 3.0691. Min Range: -3.0691

Max Act: 2.6909. Min Act: -0.0000

Data Index: 1431297 (Python Code)

Max Activating Token Index: 394

Text #5

Max Range: 3.0691. Min Range: -3.0691

Max Act: 2.8133. Min Act: -0.0000

Data Index: 1507568 (Python Code)

Max Activating Token Index: 1020

Text #6

Max Range: 3.0691. Min Range: -3.0691

Max Act: 2.6002. Min Act: -0.0000

Data Index: 1495518 (Python Code)

Max Activating Token Index: 546

Text #7

Max Range: 3.0691. Min Range: -3.0691

Max Act: 2.7372. Min Act: -0.0000

Data Index: 1584783 (Python Code)

Max Activating Token Index: 397

Text #8

Max Range: 3.0691. Min Range: -3.0691

Max Act: 2.5570. Min Act: -0.0000

Data Index: 1647011 (Python Code)

Max Activating Token Index: 373

Text #9

Max Range: 3.0691. Min Range: -3.0691

Max Act: 2.4273. Min Act: -0.0000

Data Index: 1640655 (Python Code)

Max Activating Token Index: 989

Text #10

Max Range: 3.0691. Min Range: -3.0691

Max Act: 2.5448. Min Act: -0.0000

Data Index: 1371439 (Python Code)

Max Activating Token Index: 718

Text #11

Max Range: 3.0691. Min Range: -3.0691

Max Act: 2.2173. Min Act: -0.0000

Data Index: 1418686 (Python Code)

Max Activating Token Index: 371

Text #12

Max Range: 3.0691. Min Range: -3.0691

Max Act: 1.9814. Min Act: -0.0000

Data Index: 1363162 (Python Code)

Max Activating Token Index: 852

Text #13

Max Range: 3.0691. Min Range: -3.0691

Max Act: 2.4385. Min Act: -0.0000

Data Index: 1531909 (Python Code)

Max Activating Token Index: 477

Text #14

Max Range: 3.0691. Min Range: -3.0691

Max Act: 2.3003. Min Act: -0.0000

Data Index: 1372191 (Python Code)

Max Activating Token Index: 239

Text #15

Max Range: 3.0691. Min Range: -3.0691

Max Act: 2.5094. Min Act: -0.0000

Data Index: 1614115 (Python Code)

Max Activating Token Index: 95

Text #16

Max Range: 3.0691. Min Range: -3.0691

Max Act: 2.3725. Min Act: -0.0000

Data Index: 1435842 (Python Code)

Max Activating Token Index: 310

Text #17

Max Range: 3.0691. Min Range: -3.0691

Max Act: 2.4125. Min Act: -0.0000

Data Index: 1398919 (Python Code)

Max Activating Token Index: 694

Text #18

Max Range: 3.0691. Min Range: -3.0691

Max Act: 2.1480. Min Act: -0.0000

Data Index: 1556417 (Python Code)

Max Activating Token Index: 518

Text #19

Max Range: 3.0691. Min Range: -3.0691

Max Act: 2.1032. Min Act: -0.0000

Data Index: 1594613 (Python Code)

Max Activating Token Index: 224