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

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

Neuron 3255 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: 1.7325. Min Range: -1.7325

Max Act: 1.7325. Min Act: -0.0000

Data Index: 55438 (C4 (Web Text))

Max Activating Token Index: 594

Text #1

Max Range: 1.7325. Min Range: -1.7325

Max Act: 1.5230. Min Act: -0.0000

Data Index: 597454 (C4 (Web Text))

Max Activating Token Index: 309

Text #2

Max Range: 1.7325. Min Range: -1.7325

Max Act: 1.3941. Min Act: -0.0000

Data Index: 1534722 (Python Code)

Max Activating Token Index: 727

Text #3

Max Range: 1.7325. Min Range: -1.7325

Max Act: 1.3969. Min Act: -0.0000

Data Index: 1297790 (C4 (Web Text))

Max Activating Token Index: 190

Text #4

Max Range: 1.7325. Min Range: -1.7325

Max Act: 1.1040. Min Act: -0.0000

Data Index: 1036500 (C4 (Web Text))

Max Activating Token Index: 882

Text #5

Max Range: 1.7325. Min Range: -1.7325

Max Act: 1.2440. Min Act: -0.0000

Data Index: 944512 (C4 (Web Text))

Max Activating Token Index: 857

Text #6

Max Range: 1.7325. Min Range: -1.7325

Max Act: 1.1692. Min Act: -0.0000

Data Index: 484965 (C4 (Web Text))

Max Activating Token Index: 999

Text #7

Max Range: 1.7325. Min Range: -1.7325

Max Act: 1.1626. Min Act: -0.0000

Data Index: 949963 (C4 (Web Text))

Max Activating Token Index: 477

Text #8

Max Range: 1.7325. Min Range: -1.7325

Max Act: 1.2262. Min Act: -0.0000

Data Index: 927804 (C4 (Web Text))

Max Activating Token Index: 51

Text #9

Max Range: 1.7325. Min Range: -1.7325

Max Act: 1.2523. Min Act: -0.0000

Data Index: 1449352 (Python Code)

Max Activating Token Index: 439

Text #10

Max Range: 1.7325. Min Range: -1.7325

Max Act: 1.2122. Min Act: -0.0000

Data Index: 71067 (C4 (Web Text))

Max Activating Token Index: 956

Text #11

Max Range: 1.7325. Min Range: -1.7325

Max Act: 1.2061. Min Act: -0.0000

Data Index: 1414291 (Python Code)

Max Activating Token Index: 851

Text #12

Max Range: 1.7325. Min Range: -1.7325

Max Act: 1.0887. Min Act: -0.0000

Data Index: 1294487 (C4 (Web Text))

Max Activating Token Index: 172

Text #13

Max Range: 1.7325. Min Range: -1.7325

Max Act: 1.1634. Min Act: -0.0000

Data Index: 405334 (C4 (Web Text))

Max Activating Token Index: 764

Text #14

Max Range: 1.7325. Min Range: -1.7325

Max Act: 1.2234. Min Act: -0.0000

Data Index: 1207367 (C4 (Web Text))

Max Activating Token Index: 688

Text #15

Max Range: 1.7325. Min Range: -1.7325

Max Act: 1.0815. Min Act: -0.0000

Data Index: 763687 (C4 (Web Text))

Max Activating Token Index: 355

Text #16

Max Range: 1.7325. Min Range: -1.7325

Max Act: 1.0859. Min Act: -0.0000

Data Index: 277375 (C4 (Web Text))

Max Activating Token Index: 305

Text #17

Max Range: 1.7325. Min Range: -1.7325

Max Act: 1.2202. Min Act: -0.0000

Data Index: 1356648 (C4 (Web Text))

Max Activating Token Index: 1009

Text #18

Max Range: 1.7325. Min Range: -1.7325

Max Act: 1.1545. Min Act: -0.0000

Data Index: 343486 (C4 (Web Text))

Max Activating Token Index: 960

Text #19

Max Range: 1.7325. Min Range: -1.7325

Max Act: 1.0840. Min Act: -0.0000

Data Index: 753059 (C4 (Web Text))

Max Activating Token Index: 396