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

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

Neuron 502 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3845. Min Range: -2.3845

Max Act: 2.3694. Min Act: -0.0000

Data Index: 1450100 (Python Code)

Max Activating Token Index: 733

Text #1

Max Range: 2.3845. Min Range: -2.3845

Max Act: 2.3845. Min Act: -0.0000

Data Index: 819348 (C4 (Web Text))

Max Activating Token Index: 306

Text #2

Max Range: 2.3845. Min Range: -2.3845

Max Act: 2.2006. Min Act: -0.0000

Data Index: 1519414 (Python Code)

Max Activating Token Index: 294

Text #3

Max Range: 2.3845. Min Range: -2.3845

Max Act: 2.0800. Min Act: -0.0000

Data Index: 1569977 (Python Code)

Max Activating Token Index: 22

Text #4

Max Range: 2.3845. Min Range: -2.3845

Max Act: 2.2646. Min Act: -0.0000

Data Index: 474478 (C4 (Web Text))

Max Activating Token Index: 17

Text #5

Max Range: 2.3845. Min Range: -2.3845

Max Act: 1.9912. Min Act: -0.0000

Data Index: 1590279 (Python Code)

Max Activating Token Index: 911

Text #6

Max Range: 2.3845. Min Range: -2.3845

Max Act: 2.0471. Min Act: -0.0000

Data Index: 1531391 (Python Code)

Max Activating Token Index: 482

Text #7

Max Range: 2.3845. Min Range: -2.3845

Max Act: 1.9056. Min Act: -0.0000

Data Index: 1397684 (Python Code)

Max Activating Token Index: 262

Text #8

Max Range: 2.3845. Min Range: -2.3845

Max Act: 1.8920. Min Act: -0.0000

Data Index: 1470922 (Python Code)

Max Activating Token Index: 985

Text #9

Max Range: 2.3845. Min Range: -2.3845

Max Act: 1.7770. Min Act: -0.0000

Data Index: 1512551 (Python Code)

Max Activating Token Index: 927

Text #10

Max Range: 2.3845. Min Range: -2.3845

Max Act: 1.9831. Min Act: -0.0000

Data Index: 1585067 (Python Code)

Max Activating Token Index: 450

Text #11

Max Range: 2.3845. Min Range: -2.3845

Max Act: 1.8409. Min Act: -0.0000

Data Index: 1410618 (Python Code)

Max Activating Token Index: 798

Text #12

Max Range: 2.3845. Min Range: -2.3845

Max Act: 1.8364. Min Act: -0.0000

Data Index: 1515707 (Python Code)

Max Activating Token Index: 804

Text #13

Max Range: 2.3845. Min Range: -2.3845

Max Act: 1.9502. Min Act: -0.0000

Data Index: 1564776 (Python Code)

Max Activating Token Index: 651

Text #14

Max Range: 2.3845. Min Range: -2.3845

Max Act: 1.7925. Min Act: -0.0000

Data Index: 1613144 (Python Code)

Max Activating Token Index: 361

Text #15

Max Range: 2.3845. Min Range: -2.3845

Max Act: 1.8878. Min Act: -0.0000

Data Index: 913382 (C4 (Web Text))

Max Activating Token Index: 632

Text #16

Max Range: 2.3845. Min Range: -2.3845

Max Act: 1.9760. Min Act: -0.0000

Data Index: 1428623 (Python Code)

Max Activating Token Index: 424

Text #17

Max Range: 2.3845. Min Range: -2.3845

Max Act: 1.8493. Min Act: -0.0000

Data Index: 570995 (C4 (Web Text))

Max Activating Token Index: 194

Text #18

Max Range: 2.3845. Min Range: -2.3845

Max Act: 1.7462. Min Act: -0.0000

Data Index: 153373 (C4 (Web Text))

Max Activating Token Index: 195

Text #19

Max Range: 2.3845. Min Range: -2.3845

Max Act: 1.8491. Min Act: -0.0000

Data Index: 1498057 (Python Code)

Max Activating Token Index: 527