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

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

Neuron 4060 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1388. Min Range: -2.1388

Max Act: 2.1388. Min Act: -0.0000

Data Index: 1616847 (Python Code)

Max Activating Token Index: 798

Text #1

Max Range: 2.1388. Min Range: -2.1388

Max Act: 1.6038. Min Act: -0.0000

Data Index: 1528098 (Python Code)

Max Activating Token Index: 851

Text #2

Max Range: 2.1388. Min Range: -2.1388

Max Act: 1.5818. Min Act: -0.0000

Data Index: 191904 (C4 (Web Text))

Max Activating Token Index: 237

Text #3

Max Range: 2.1388. Min Range: -2.1388

Max Act: 1.6566. Min Act: -0.0000

Data Index: 1367005 (Python Code)

Max Activating Token Index: 349

Text #4

Max Range: 2.1388. Min Range: -2.1388

Max Act: 1.3728. Min Act: -0.0000

Data Index: 1526245 (Python Code)

Max Activating Token Index: 642

Text #5

Max Range: 2.1388. Min Range: -2.1388

Max Act: 1.3990. Min Act: -0.0000

Data Index: 1304612 (C4 (Web Text))

Max Activating Token Index: 583

Text #6

Max Range: 2.1388. Min Range: -2.1388

Max Act: 1.2865. Min Act: -0.0000

Data Index: 1543642 (Python Code)

Max Activating Token Index: 735

Text #7

Max Range: 2.1388. Min Range: -2.1388

Max Act: 1.2463. Min Act: -0.0000

Data Index: 280907 (C4 (Web Text))

Max Activating Token Index: 951

Text #8

Max Range: 2.1388. Min Range: -2.1388

Max Act: 1.3222. Min Act: -0.0000

Data Index: 1423680 (Python Code)

Max Activating Token Index: 449

Text #9

Max Range: 2.1388. Min Range: -2.1388

Max Act: 1.2144. Min Act: -0.0000

Data Index: 683454 (C4 (Web Text))

Max Activating Token Index: 951

Text #10

Max Range: 2.1388. Min Range: -2.1388

Max Act: 1.2095. Min Act: -0.0000

Data Index: 490164 (C4 (Web Text))

Max Activating Token Index: 125

Text #11

Max Range: 2.1388. Min Range: -2.1388

Max Act: 1.2995. Min Act: -0.0000

Data Index: 1443251 (Python Code)

Max Activating Token Index: 1003

Text #12

Max Range: 2.1388. Min Range: -2.1388

Max Act: 1.1847. Min Act: -0.0000

Data Index: 1584656 (Python Code)

Max Activating Token Index: 999

Text #13

Max Range: 2.1388. Min Range: -2.1388

Max Act: 1.2265. Min Act: -0.0000

Data Index: 1403492 (Python Code)

Max Activating Token Index: 403

Text #14

Max Range: 2.1388. Min Range: -2.1388

Max Act: 1.1811. Min Act: -0.0000

Data Index: 453038 (C4 (Web Text))

Max Activating Token Index: 661

Text #15

Max Range: 2.1388. Min Range: -2.1388

Max Act: 1.2085. Min Act: -0.0000

Data Index: 1497191 (Python Code)

Max Activating Token Index: 450

Text #16

Max Range: 2.1388. Min Range: -2.1388

Max Act: 1.1766. Min Act: -0.0000

Data Index: 407791 (C4 (Web Text))

Max Activating Token Index: 37

Text #17

Max Range: 2.1388. Min Range: -2.1388

Max Act: 1.1149. Min Act: -0.0000

Data Index: 584397 (C4 (Web Text))

Max Activating Token Index: 377

Text #18

Max Range: 2.1388. Min Range: -2.1388

Max Act: 1.1568. Min Act: -0.0000

Data Index: 51028 (C4 (Web Text))

Max Activating Token Index: 588

Text #19

Max Range: 2.1388. Min Range: -2.1388

Max Act: 1.1126. Min Act: -0.0000

Data Index: 1412112 (Python Code)

Max Activating Token Index: 806