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

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

Neuron 857 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.1234. Min Range: -5.1234

Max Act: 5.1234. Min Act: -0.0000

Data Index: 1534185 (Python Code)

Max Activating Token Index: 544

Text #1

Max Range: 5.1234. Min Range: -5.1234

Max Act: 4.4559. Min Act: -0.0000

Data Index: 1411170 (Python Code)

Max Activating Token Index: 583

Text #2

Max Range: 5.1234. Min Range: -5.1234

Max Act: 4.6109. Min Act: -0.0000

Data Index: 1462836 (Python Code)

Max Activating Token Index: 579

Text #3

Max Range: 5.1234. Min Range: -5.1234

Max Act: 4.3324. Min Act: -0.0000

Data Index: 1535702 (Python Code)

Max Activating Token Index: 793

Text #4

Max Range: 5.1234. Min Range: -5.1234

Max Act: 4.0893. Min Act: -0.0000

Data Index: 1578970 (Python Code)

Max Activating Token Index: 204

Text #5

Max Range: 5.1234. Min Range: -5.1234

Max Act: 4.2960. Min Act: -0.0000

Data Index: 1630535 (Python Code)

Max Activating Token Index: 226

Text #6

Max Range: 5.1234. Min Range: -5.1234

Max Act: 4.0821. Min Act: -0.0000

Data Index: 1554011 (Python Code)

Max Activating Token Index: 730

Text #7

Max Range: 5.1234. Min Range: -5.1234

Max Act: 4.0961. Min Act: -0.0000

Data Index: 1523214 (Python Code)

Max Activating Token Index: 769

Text #8

Max Range: 5.1234. Min Range: -5.1234

Max Act: 4.0824. Min Act: -0.0000

Data Index: 1582954 (Python Code)

Max Activating Token Index: 699

Text #9

Max Range: 5.1234. Min Range: -5.1234

Max Act: 3.8372. Min Act: -0.0000

Data Index: 1409194 (Python Code)

Max Activating Token Index: 314

Text #10

Max Range: 5.1234. Min Range: -5.1234

Max Act: 3.8755. Min Act: -0.0000

Data Index: 1563407 (Python Code)

Max Activating Token Index: 545

Text #11

Max Range: 5.1234. Min Range: -5.1234

Max Act: 3.7072. Min Act: -0.0000

Data Index: 1489563 (Python Code)

Max Activating Token Index: 141

Text #12

Max Range: 5.1234. Min Range: -5.1234

Max Act: 3.5335. Min Act: -0.0000

Data Index: 1593272 (Python Code)

Max Activating Token Index: 1019

Text #13

Max Range: 5.1234. Min Range: -5.1234

Max Act: 3.6592. Min Act: -0.0000

Data Index: 1523786 (Python Code)

Max Activating Token Index: 1000

Text #14

Max Range: 5.1234. Min Range: -5.1234

Max Act: 3.8500. Min Act: -0.0000

Data Index: 1607546 (Python Code)

Max Activating Token Index: 205

Text #15

Max Range: 5.1234. Min Range: -5.1234

Max Act: 3.6705. Min Act: -0.0000

Data Index: 1435504 (Python Code)

Max Activating Token Index: 534

Text #16

Max Range: 5.1234. Min Range: -5.1234

Max Act: 3.8030. Min Act: -0.0000

Data Index: 1527316 (Python Code)

Max Activating Token Index: 465

Text #17

Max Range: 5.1234. Min Range: -5.1234

Max Act: 3.8050. Min Act: -0.0000

Data Index: 1586542 (Python Code)

Max Activating Token Index: 773

Text #18

Max Range: 5.1234. Min Range: -5.1234

Max Act: 3.8049. Min Act: -0.0000

Data Index: 1517982 (Python Code)

Max Activating Token Index: 427

Text #19

Max Range: 5.1234. Min Range: -5.1234

Max Act: 3.6492. Min Act: -0.0000

Data Index: 1607941 (Python Code)

Max Activating Token Index: 406