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

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

Neuron 2385 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: 2.5414. Min Range: -2.5414

Max Act: 2.3829. Min Act: -0.0000

Data Index: 1499595 (Python Code)

Max Activating Token Index: 856

Text #1

Max Range: 2.5414. Min Range: -2.5414

Max Act: 2.3372. Min Act: -0.0000

Data Index: 921168 (C4 (Web Text))

Max Activating Token Index: 225

Text #2

Max Range: 2.5414. Min Range: -2.5414

Max Act: 2.4436. Min Act: -0.0000

Data Index: 1530449 (Python Code)

Max Activating Token Index: 768

Text #3

Max Range: 2.5414. Min Range: -2.5414

Max Act: 2.3097. Min Act: -0.0000

Data Index: 1422797 (Python Code)

Max Activating Token Index: 758

Text #4

Max Range: 2.5414. Min Range: -2.5414

Max Act: 2.5414. Min Act: -0.0000

Data Index: 1601724 (Python Code)

Max Activating Token Index: 1008

Text #5

Max Range: 2.5414. Min Range: -2.5414

Max Act: 1.9396. Min Act: -0.0000

Data Index: 213789 (C4 (Web Text))

Max Activating Token Index: 433

Text #6

Max Range: 2.5414. Min Range: -2.5414

Max Act: 2.2016. Min Act: -0.0000

Data Index: 1442686 (Python Code)

Max Activating Token Index: 772

Text #7

Max Range: 2.5414. Min Range: -2.5414

Max Act: 2.1489. Min Act: -0.0000

Data Index: 1432904 (Python Code)

Max Activating Token Index: 808

Text #8

Max Range: 2.5414. Min Range: -2.5414

Max Act: 2.0005. Min Act: -0.0000

Data Index: 1507053 (Python Code)

Max Activating Token Index: 66

Text #9

Max Range: 2.5414. Min Range: -2.5414

Max Act: 1.8268. Min Act: -0.0000

Data Index: 190150 (C4 (Web Text))

Max Activating Token Index: 831

Text #10

Max Range: 2.5414. Min Range: -2.5414

Max Act: 1.8364. Min Act: -0.0000

Data Index: 1553341 (Python Code)

Max Activating Token Index: 982

Text #11

Max Range: 2.5414. Min Range: -2.5414

Max Act: 1.7458. Min Act: -0.0000

Data Index: 1547800 (Python Code)

Max Activating Token Index: 973

Text #12

Max Range: 2.5414. Min Range: -2.5414

Max Act: 1.7210. Min Act: -0.0000

Data Index: 955385 (C4 (Web Text))

Max Activating Token Index: 863

Text #13

Max Range: 2.5414. Min Range: -2.5414

Max Act: 1.7138. Min Act: -0.0000

Data Index: 1478493 (Python Code)

Max Activating Token Index: 505

Text #14

Max Range: 2.5414. Min Range: -2.5414

Max Act: 1.8105. Min Act: -0.0000

Data Index: 1406169 (Python Code)

Max Activating Token Index: 78

Text #15

Max Range: 2.5414. Min Range: -2.5414

Max Act: 1.8294. Min Act: -0.0000

Data Index: 1646140 (Python Code)

Max Activating Token Index: 943

Text #16

Max Range: 2.5414. Min Range: -2.5414

Max Act: 1.7819. Min Act: -0.0000

Data Index: 1397150 (Python Code)

Max Activating Token Index: 96

Text #17

Max Range: 2.5414. Min Range: -2.5414

Max Act: 1.7919. Min Act: -0.0000

Data Index: 413290 (C4 (Web Text))

Max Activating Token Index: 714

Text #18

Max Range: 2.5414. Min Range: -2.5414

Max Act: 1.7787. Min Act: -0.0000

Data Index: 1197630 (C4 (Web Text))

Max Activating Token Index: 253

Text #19

Max Range: 2.5414. Min Range: -2.5414

Max Act: 1.6995. Min Act: -0.0000

Data Index: 1618735 (Python Code)

Max Activating Token Index: 984