Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2367 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.8613. Min Range: -0.8613

Max Act: 0.8613. Min Act: -0.0000

Data Index: 1475940 (Python Code)

Max Activating Token Index: 218

Text #1

Max Range: 0.8613. Min Range: -0.8613

Max Act: 0.7524. Min Act: -0.0000

Data Index: 1428928 (Python Code)

Max Activating Token Index: 962

Text #2

Max Range: 0.8613. Min Range: -0.8613

Max Act: 0.7285. Min Act: -0.0000

Data Index: 1409588 (Python Code)

Max Activating Token Index: 242

Text #3

Max Range: 0.8613. Min Range: -0.8613

Max Act: 0.7397. Min Act: -0.0000

Data Index: 1468483 (Python Code)

Max Activating Token Index: 438

Text #4

Max Range: 0.8613. Min Range: -0.8613

Max Act: 0.7621. Min Act: -0.0000

Data Index: 1484972 (Python Code)

Max Activating Token Index: 254

Text #5

Max Range: 0.8613. Min Range: -0.8613

Max Act: 0.7737. Min Act: -0.0000

Data Index: 1456792 (Python Code)

Max Activating Token Index: 663

Text #6

Max Range: 0.8613. Min Range: -0.8613

Max Act: 0.7280. Min Act: -0.0000

Data Index: 1423709 (Python Code)

Max Activating Token Index: 131

Text #7

Max Range: 0.8613. Min Range: -0.8613

Max Act: 0.7258. Min Act: -0.0000

Data Index: 1463570 (Python Code)

Max Activating Token Index: 359

Text #8

Max Range: 0.8613. Min Range: -0.8613

Max Act: 0.7414. Min Act: -0.0000

Data Index: 1626999 (Python Code)

Max Activating Token Index: 125

Text #9

Max Range: 0.8613. Min Range: -0.8613

Max Act: 0.6756. Min Act: -0.0001

Data Index: 1432290 (Python Code)

Max Activating Token Index: 819

Text #10

Max Range: 0.8613. Min Range: -0.8613

Max Act: 0.6949. Min Act: -0.0000

Data Index: 1417606 (Python Code)

Max Activating Token Index: 709

Text #11

Max Range: 0.8613. Min Range: -0.8613

Max Act: 0.6878. Min Act: -0.0000

Data Index: 1499943 (Python Code)

Max Activating Token Index: 127

Text #12

Max Range: 0.8613. Min Range: -0.8613

Max Act: 0.7607. Min Act: -0.0000

Data Index: 1548587 (Python Code)

Max Activating Token Index: 167

Text #13

Max Range: 0.8613. Min Range: -0.8613

Max Act: 0.7291. Min Act: -0.0000

Data Index: 1556081 (Python Code)

Max Activating Token Index: 177

Text #14

Max Range: 0.8613. Min Range: -0.8613

Max Act: 0.6826. Min Act: -0.0000

Data Index: 1361362 (Python Code)

Max Activating Token Index: 437

Text #15

Max Range: 0.8613. Min Range: -0.8613

Max Act: 0.6704. Min Act: -0.0000

Data Index: 1537882 (Python Code)

Max Activating Token Index: 903

Text #16

Max Range: 0.8613. Min Range: -0.8613

Max Act: 0.6755. Min Act: -0.0000

Data Index: 1630292 (Python Code)

Max Activating Token Index: 664

Text #17

Max Range: 0.8613. Min Range: -0.8613

Max Act: 0.6920. Min Act: -0.0000

Data Index: 1451392 (Python Code)

Max Activating Token Index: 188

Text #18

Max Range: 0.8613. Min Range: -0.8613

Max Act: 0.6902. Min Act: -0.0000

Data Index: 1544382 (Python Code)

Max Activating Token Index: 419

Text #19

Max Range: 0.8613. Min Range: -0.8613

Max Act: 0.6632. Min Act: -0.0000

Data Index: 1373109 (Python Code)

Max Activating Token Index: 871