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

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

Neuron 6118 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: 0.9676. Min Range: -0.9676

Max Act: 0.9676. Min Act: -0.0000

Data Index: 24667 (C4 (Web Text))

Max Activating Token Index: 253

Text #1

Max Range: 0.9676. Min Range: -0.9676

Max Act: 0.7765. Min Act: -0.0000

Data Index: 68978 (C4 (Web Text))

Max Activating Token Index: 505

Text #2

Max Range: 0.9676. Min Range: -0.9676

Max Act: 0.7764. Min Act: -0.0000

Data Index: 1181469 (C4 (Web Text))

Max Activating Token Index: 653

Text #3

Max Range: 0.9676. Min Range: -0.9676

Max Act: 0.7293. Min Act: -0.0000

Data Index: 775341 (C4 (Web Text))

Max Activating Token Index: 731

Text #4

Max Range: 0.9676. Min Range: -0.9676

Max Act: 0.7617. Min Act: -0.0000

Data Index: 1241572 (C4 (Web Text))

Max Activating Token Index: 496

Text #5

Max Range: 0.9676. Min Range: -0.9676

Max Act: 0.8549. Min Act: -0.0000

Data Index: 379894 (C4 (Web Text))

Max Activating Token Index: 376

Text #6

Max Range: 0.9676. Min Range: -0.9676

Max Act: 0.7769. Min Act: -0.0000

Data Index: 1397622 (Python Code)

Max Activating Token Index: 104

Text #7

Max Range: 0.9676. Min Range: -0.9676

Max Act: 0.7048. Min Act: -0.0000

Data Index: 142491 (C4 (Web Text))

Max Activating Token Index: 638

Text #8

Max Range: 0.9676. Min Range: -0.9676

Max Act: 0.7002. Min Act: -0.0000

Data Index: 657549 (C4 (Web Text))

Max Activating Token Index: 838

Text #9

Max Range: 0.9676. Min Range: -0.9676

Max Act: 0.7227. Min Act: -0.0000

Data Index: 63401 (C4 (Web Text))

Max Activating Token Index: 77

Text #10

Max Range: 0.9676. Min Range: -0.9676

Max Act: 0.7157. Min Act: -0.0000

Data Index: 1240432 (C4 (Web Text))

Max Activating Token Index: 945

Text #11

Max Range: 0.9676. Min Range: -0.9676

Max Act: 0.6871. Min Act: -0.0000

Data Index: 1129817 (C4 (Web Text))

Max Activating Token Index: 524

Text #12

Max Range: 0.9676. Min Range: -0.9676

Max Act: 0.7715. Min Act: -0.0000

Data Index: 905330 (C4 (Web Text))

Max Activating Token Index: 520

Text #13

Max Range: 0.9676. Min Range: -0.9676

Max Act: 0.7364. Min Act: -0.0000

Data Index: 1241275 (C4 (Web Text))

Max Activating Token Index: 60

Text #14

Max Range: 0.9676. Min Range: -0.9676

Max Act: 0.7295. Min Act: -0.0000

Data Index: 1390256 (Python Code)

Max Activating Token Index: 257

Text #15

Max Range: 0.9676. Min Range: -0.9676

Max Act: 0.6848. Min Act: -0.0000

Data Index: 224933 (C4 (Web Text))

Max Activating Token Index: 361

Text #16

Max Range: 0.9676. Min Range: -0.9676

Max Act: 0.6628. Min Act: -0.0000

Data Index: 359421 (C4 (Web Text))

Max Activating Token Index: 989

Text #17

Max Range: 0.9676. Min Range: -0.9676

Max Act: 0.6904. Min Act: -0.0000

Data Index: 1363277 (Python Code)

Max Activating Token Index: 806

Text #18

Max Range: 0.9676. Min Range: -0.9676

Max Act: 0.6893. Min Act: -0.0000

Data Index: 1521494 (Python Code)

Max Activating Token Index: 595

Text #19

Max Range: 0.9676. Min Range: -0.9676

Max Act: 0.6436. Min Act: -0.0000

Data Index: 758955 (C4 (Web Text))

Max Activating Token Index: 206