Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 537 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.9540. Min Range: -0.9540

Max Act: 0.9540. Min Act: -0.0001

Data Index: 1535490 (Python Code)

Max Activating Token Index: 482

Text #1

Max Range: 0.9540. Min Range: -0.9540

Max Act: 0.9142. Min Act: -0.0001

Data Index: 1376722 (Python Code)

Max Activating Token Index: 394

Text #2

Max Range: 0.9540. Min Range: -0.9540

Max Act: 0.9401. Min Act: -0.0001

Data Index: 1363664 (Python Code)

Max Activating Token Index: 883

Text #3

Max Range: 0.9540. Min Range: -0.9540

Max Act: 0.8580. Min Act: -0.0001

Data Index: 1566091 (Python Code)

Max Activating Token Index: 536

Text #4

Max Range: 0.9540. Min Range: -0.9540

Max Act: 0.9291. Min Act: -0.0001

Data Index: 180041 (C4 (Web Text))

Max Activating Token Index: 344

Text #5

Max Range: 0.9540. Min Range: -0.9540

Max Act: 0.7638. Min Act: -0.0001

Data Index: 1529135 (Python Code)

Max Activating Token Index: 697

Text #6

Max Range: 0.9540. Min Range: -0.9540

Max Act: 0.8845. Min Act: -0.0001

Data Index: 1512899 (Python Code)

Max Activating Token Index: 220

Text #7

Max Range: 0.9540. Min Range: -0.9540

Max Act: 0.6798. Min Act: -0.0001

Data Index: 1652398 (Python Code)

Max Activating Token Index: 266

Text #8

Max Range: 0.9540. Min Range: -0.9540

Max Act: 0.6656. Min Act: -0.0001

Data Index: 1471843 (Python Code)

Max Activating Token Index: 565

Text #9

Max Range: 0.9540. Min Range: -0.9540

Max Act: 0.7546. Min Act: -0.0001

Data Index: 1610716 (Python Code)

Max Activating Token Index: 349

Text #10

Max Range: 0.9540. Min Range: -0.9540

Max Act: 0.7784. Min Act: -0.0001

Data Index: 1583619 (Python Code)

Max Activating Token Index: 352

Text #11

Max Range: 0.9540. Min Range: -0.9540

Max Act: 0.7986. Min Act: -0.0001

Data Index: 1528838 (Python Code)

Max Activating Token Index: 952

Text #12

Max Range: 0.9540. Min Range: -0.9540

Max Act: 0.7203. Min Act: -0.0001

Data Index: 32666 (C4 (Web Text))

Max Activating Token Index: 912

Text #13

Max Range: 0.9540. Min Range: -0.9540

Max Act: 0.7635. Min Act: -0.0001

Data Index: 1630217 (Python Code)

Max Activating Token Index: 155

Text #14

Max Range: 0.9540. Min Range: -0.9540

Max Act: 0.7319. Min Act: -0.0001

Data Index: 1375352 (Python Code)

Max Activating Token Index: 256

Text #15

Max Range: 0.9540. Min Range: -0.9540

Max Act: 0.7804. Min Act: -0.0001

Data Index: 603317 (C4 (Web Text))

Max Activating Token Index: 547

Text #16

Max Range: 0.9540. Min Range: -0.9540

Max Act: 0.7738. Min Act: -0.0001

Data Index: 707327 (C4 (Web Text))

Max Activating Token Index: 900

Text #17

Max Range: 0.9540. Min Range: -0.9540

Max Act: 0.7983. Min Act: -0.0001

Data Index: 1648208 (Python Code)

Max Activating Token Index: 84

Text #18

Max Range: 0.9540. Min Range: -0.9540

Max Act: 0.7226. Min Act: -0.0001

Data Index: 1428972 (Python Code)

Max Activating Token Index: 432

Text #19

Max Range: 0.9540. Min Range: -0.9540

Max Act: 0.6647. Min Act: -0.0001

Data Index: 998814 (C4 (Web Text))

Max Activating Token Index: 940