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

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

Neuron 2729 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1427. Min Range: -3.1427

Max Act: 3.0899. Min Act: -0.0000

Data Index: 1395811 (Python Code)

Max Activating Token Index: 572

Text #1

Max Range: 3.1427. Min Range: -3.1427

Max Act: 2.8801. Min Act: -0.0000

Data Index: 1510634 (Python Code)

Max Activating Token Index: 713

Text #2

Max Range: 3.1427. Min Range: -3.1427

Max Act: 3.1427. Min Act: -0.0000

Data Index: 1414939 (Python Code)

Max Activating Token Index: 818

Text #3

Max Range: 3.1427. Min Range: -3.1427

Max Act: 2.9976. Min Act: -0.0000

Data Index: 1444019 (Python Code)

Max Activating Token Index: 924

Text #4

Max Range: 3.1427. Min Range: -3.1427

Max Act: 2.6824. Min Act: -0.0000

Data Index: 1602921 (Python Code)

Max Activating Token Index: 488

Text #5

Max Range: 3.1427. Min Range: -3.1427

Max Act: 2.6513. Min Act: -0.0000

Data Index: 1619414 (Python Code)

Max Activating Token Index: 941

Text #6

Max Range: 3.1427. Min Range: -3.1427

Max Act: 2.9240. Min Act: -0.0000

Data Index: 1627324 (Python Code)

Max Activating Token Index: 848

Text #7

Max Range: 3.1427. Min Range: -3.1427

Max Act: 2.9254. Min Act: -0.0000

Data Index: 1517498 (Python Code)

Max Activating Token Index: 357

Text #8

Max Range: 3.1427. Min Range: -3.1427

Max Act: 2.9766. Min Act: -0.0000

Data Index: 1629879 (Python Code)

Max Activating Token Index: 595

Text #9

Max Range: 3.1427. Min Range: -3.1427

Max Act: 2.7111. Min Act: -0.0000

Data Index: 1449619 (Python Code)

Max Activating Token Index: 806

Text #10

Max Range: 3.1427. Min Range: -3.1427

Max Act: 2.8329. Min Act: -0.0000

Data Index: 1569953 (Python Code)

Max Activating Token Index: 667

Text #11

Max Range: 3.1427. Min Range: -3.1427

Max Act: 2.8173. Min Act: -0.0000

Data Index: 1617802 (Python Code)

Max Activating Token Index: 606

Text #12

Max Range: 3.1427. Min Range: -3.1427

Max Act: 2.8208. Min Act: -0.0000

Data Index: 1419095 (Python Code)

Max Activating Token Index: 789

Text #13

Max Range: 3.1427. Min Range: -3.1427

Max Act: 2.7898. Min Act: -0.0000

Data Index: 1613355 (Python Code)

Max Activating Token Index: 214

Text #14

Max Range: 3.1427. Min Range: -3.1427

Max Act: 2.6361. Min Act: -0.0000

Data Index: 1628576 (Python Code)

Max Activating Token Index: 258

Text #15

Max Range: 3.1427. Min Range: -3.1427

Max Act: 2.7533. Min Act: -0.0000

Data Index: 1419491 (Python Code)

Max Activating Token Index: 193

Text #16

Max Range: 3.1427. Min Range: -3.1427

Max Act: 2.8468. Min Act: -0.0000

Data Index: 1637067 (Python Code)

Max Activating Token Index: 859

Text #17

Max Range: 3.1427. Min Range: -3.1427

Max Act: 2.8432. Min Act: -0.0000

Data Index: 1402734 (Python Code)

Max Activating Token Index: 468

Text #18

Max Range: 3.1427. Min Range: -3.1427

Max Act: 2.6989. Min Act: -0.0000

Data Index: 1470028 (Python Code)

Max Activating Token Index: 779

Text #19

Max Range: 3.1427. Min Range: -3.1427

Max Act: 2.6806. Min Act: -0.0000

Data Index: 1375154 (Python Code)

Max Activating Token Index: 717