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

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

Neuron 3336 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3285. Min Range: -2.3285

Max Act: 2.3285. Min Act: -0.0000

Data Index: 1383164 (Python Code)

Max Activating Token Index: 39

Text #1

Max Range: 2.3285. Min Range: -2.3285

Max Act: 2.2321. Min Act: -0.0000

Data Index: 1615828 (Python Code)

Max Activating Token Index: 66

Text #2

Max Range: 2.3285. Min Range: -2.3285

Max Act: 2.0921. Min Act: -0.0000

Data Index: 1586750 (Python Code)

Max Activating Token Index: 119

Text #3

Max Range: 2.3285. Min Range: -2.3285

Max Act: 1.8109. Min Act: -0.0000

Data Index: 718437 (C4 (Web Text))

Max Activating Token Index: 6

Text #4

Max Range: 2.3285. Min Range: -2.3285

Max Act: 1.9599. Min Act: -0.0000

Data Index: 1639314 (Python Code)

Max Activating Token Index: 88

Text #5

Max Range: 2.3285. Min Range: -2.3285

Max Act: 1.7870. Min Act: -0.0000

Data Index: 1394384 (Python Code)

Max Activating Token Index: 581

Text #6

Max Range: 2.3285. Min Range: -2.3285

Max Act: 1.7579. Min Act: -0.0000

Data Index: 1614529 (Python Code)

Max Activating Token Index: 1021

Text #7

Max Range: 2.3285. Min Range: -2.3285

Max Act: 1.7715. Min Act: -0.0000

Data Index: 1628539 (Python Code)

Max Activating Token Index: 116

Text #8

Max Range: 2.3285. Min Range: -2.3285

Max Act: 1.7736. Min Act: -0.0000

Data Index: 1560868 (Python Code)

Max Activating Token Index: 122

Text #9

Max Range: 2.3285. Min Range: -2.3285

Max Act: 1.8017. Min Act: -0.0000

Data Index: 1386800 (Python Code)

Max Activating Token Index: 223

Text #10

Max Range: 2.3285. Min Range: -2.3285

Max Act: 1.7417. Min Act: -0.0000

Data Index: 1602817 (Python Code)

Max Activating Token Index: 316

Text #11

Max Range: 2.3285. Min Range: -2.3285

Max Act: 1.8004. Min Act: -0.0000

Data Index: 1368197 (Python Code)

Max Activating Token Index: 236

Text #12

Max Range: 2.3285. Min Range: -2.3285

Max Act: 1.7758. Min Act: -0.0000

Data Index: 1513436 (Python Code)

Max Activating Token Index: 760

Text #13

Max Range: 2.3285. Min Range: -2.3285

Max Act: 1.6642. Min Act: -0.0000

Data Index: 598705 (C4 (Web Text))

Max Activating Token Index: 1000

Text #14

Max Range: 2.3285. Min Range: -2.3285

Max Act: 1.6804. Min Act: -0.0000

Data Index: 1630049 (Python Code)

Max Activating Token Index: 909

Text #15

Max Range: 2.3285. Min Range: -2.3285

Max Act: 1.6221. Min Act: -0.0000

Data Index: 1521902 (Python Code)

Max Activating Token Index: 899

Text #16

Max Range: 2.3285. Min Range: -2.3285

Max Act: 1.6848. Min Act: -0.0000

Data Index: 1212922 (C4 (Web Text))

Max Activating Token Index: 662

Text #17

Max Range: 2.3285. Min Range: -2.3285

Max Act: 1.6732. Min Act: -0.0000

Data Index: 1512748 (Python Code)

Max Activating Token Index: 485

Text #18

Max Range: 2.3285. Min Range: -2.3285

Max Act: 1.6822. Min Act: -0.0000

Data Index: 1567359 (Python Code)

Max Activating Token Index: 539

Text #19

Max Range: 2.3285. Min Range: -2.3285

Max Act: 1.6369. Min Act: -0.0000

Data Index: 1374075 (Python Code)

Max Activating Token Index: 516