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

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

Neuron 1 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6373. Min Range: -0.6373

Max Act: 0.6039. Min Act: -0.0000

Data Index: 305863 (C4 (Web Text))

Max Activating Token Index: 179

Text #1

Max Range: 0.6373. Min Range: -0.6373

Max Act: 0.6373. Min Act: -0.0000

Data Index: 1561015 (Python Code)

Max Activating Token Index: 812

Text #2

Max Range: 0.6373. Min Range: -0.6373

Max Act: 0.5879. Min Act: -0.0000

Data Index: 1543118 (Python Code)

Max Activating Token Index: 731

Text #3

Max Range: 0.6373. Min Range: -0.6373

Max Act: 0.6185. Min Act: -0.0000

Data Index: 1395066 (Python Code)

Max Activating Token Index: 977

Text #4

Max Range: 0.6373. Min Range: -0.6373

Max Act: 0.5524. Min Act: -0.0000

Data Index: 1539954 (Python Code)

Max Activating Token Index: 881

Text #5

Max Range: 0.6373. Min Range: -0.6373

Max Act: 0.5340. Min Act: -0.0000

Data Index: 1473216 (Python Code)

Max Activating Token Index: 879

Text #6

Max Range: 0.6373. Min Range: -0.6373

Max Act: 0.5304. Min Act: -0.0000

Data Index: 1643993 (Python Code)

Max Activating Token Index: 724

Text #7

Max Range: 0.6373. Min Range: -0.6373

Max Act: 0.5511. Min Act: -0.0000

Data Index: 1394149 (Python Code)

Max Activating Token Index: 876

Text #8

Max Range: 0.6373. Min Range: -0.6373

Max Act: 0.5725. Min Act: -0.0000

Data Index: 1549597 (Python Code)

Max Activating Token Index: 875

Text #9

Max Range: 0.6373. Min Range: -0.6373

Max Act: 0.5676. Min Act: -0.0000

Data Index: 1653411 (Python Code)

Max Activating Token Index: 736

Text #10

Max Range: 0.6373. Min Range: -0.6373

Max Act: 0.6129. Min Act: -0.0000

Data Index: 1436183 (Python Code)

Max Activating Token Index: 995

Text #11

Max Range: 0.6373. Min Range: -0.6373

Max Act: 0.5700. Min Act: -0.0000

Data Index: 1596868 (Python Code)

Max Activating Token Index: 395

Text #12

Max Range: 0.6373. Min Range: -0.6373

Max Act: 0.5611. Min Act: -0.0000

Data Index: 1408950 (Python Code)

Max Activating Token Index: 533

Text #13

Max Range: 0.6373. Min Range: -0.6373

Max Act: 0.5394. Min Act: -0.0000

Data Index: 1490042 (Python Code)

Max Activating Token Index: 565

Text #14

Max Range: 0.6373. Min Range: -0.6373

Max Act: 0.5384. Min Act: -0.0000

Data Index: 390828 (C4 (Web Text))

Max Activating Token Index: 972

Text #15

Max Range: 0.6373. Min Range: -0.6373

Max Act: 0.5647. Min Act: -0.0000

Data Index: 1600575 (Python Code)

Max Activating Token Index: 462

Text #16

Max Range: 0.6373. Min Range: -0.6373

Max Act: 0.5652. Min Act: -0.0000

Data Index: 1433307 (Python Code)

Max Activating Token Index: 570

Text #17

Max Range: 0.6373. Min Range: -0.6373

Max Act: 0.5288. Min Act: -0.0000

Data Index: 1451188 (Python Code)

Max Activating Token Index: 661

Text #18

Max Range: 0.6373. Min Range: -0.6373

Max Act: 0.5785. Min Act: -0.0000

Data Index: 1275072 (C4 (Web Text))

Max Activating Token Index: 157

Text #19

Max Range: 0.6373. Min Range: -0.6373

Max Act: 0.4799. Min Act: -0.0000

Data Index: 1591255 (Python Code)

Max Activating Token Index: 864