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

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

Neuron 2977 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.5091. Min Range: -0.5091

Max Act: 0.5091. Min Act: -0.0002

Data Index: 1466302 (Python Code)

Max Activating Token Index: 690

Text #1

Max Range: 0.5091. Min Range: -0.5091

Max Act: 0.4604. Min Act: -0.0002

Data Index: 1573545 (Python Code)

Max Activating Token Index: 484

Text #2

Max Range: 0.5091. Min Range: -0.5091

Max Act: 0.4368. Min Act: -0.0002

Data Index: 1420026 (Python Code)

Max Activating Token Index: 415

Text #3

Max Range: 0.5091. Min Range: -0.5091

Max Act: 0.4142. Min Act: -0.0002

Data Index: 1631253 (Python Code)

Max Activating Token Index: 49

Text #4

Max Range: 0.5091. Min Range: -0.5091

Max Act: 0.4146. Min Act: -0.0002

Data Index: 1641712 (Python Code)

Max Activating Token Index: 772

Text #5

Max Range: 0.5091. Min Range: -0.5091

Max Act: 0.3941. Min Act: -0.0002

Data Index: 1402131 (Python Code)

Max Activating Token Index: 447

Text #6

Max Range: 0.5091. Min Range: -0.5091

Max Act: 0.3899. Min Act: -0.0002

Data Index: 1627582 (Python Code)

Max Activating Token Index: 452

Text #7

Max Range: 0.5091. Min Range: -0.5091

Max Act: 0.3965. Min Act: -0.0002

Data Index: 1369704 (Python Code)

Max Activating Token Index: 770

Text #8

Max Range: 0.5091. Min Range: -0.5091

Max Act: 0.3963. Min Act: -0.0002

Data Index: 1499514 (Python Code)

Max Activating Token Index: 144

Text #9

Max Range: 0.5091. Min Range: -0.5091

Max Act: 0.3927. Min Act: -0.0002

Data Index: 1406299 (Python Code)

Max Activating Token Index: 20

Text #10

Max Range: 0.5091. Min Range: -0.5091

Max Act: 0.3898. Min Act: -0.0002

Data Index: 1495165 (Python Code)

Max Activating Token Index: 755

Text #11

Max Range: 0.5091. Min Range: -0.5091

Max Act: 0.3784. Min Act: -0.0002

Data Index: 1634163 (Python Code)

Max Activating Token Index: 537

Text #12

Max Range: 0.5091. Min Range: -0.5091

Max Act: 0.3907. Min Act: -0.0002

Data Index: 1391501 (Python Code)

Max Activating Token Index: 849

Text #13

Max Range: 0.5091. Min Range: -0.5091

Max Act: 0.3876. Min Act: -0.0002

Data Index: 1398235 (Python Code)

Max Activating Token Index: 618

Text #14

Max Range: 0.5091. Min Range: -0.5091

Max Act: 0.3845. Min Act: -0.0002

Data Index: 1555530 (Python Code)

Max Activating Token Index: 408

Text #15

Max Range: 0.5091. Min Range: -0.5091

Max Act: 0.3754. Min Act: -0.0002

Data Index: 1516077 (Python Code)

Max Activating Token Index: 934

Text #16

Max Range: 0.5091. Min Range: -0.5091

Max Act: 0.3790. Min Act: -0.0002

Data Index: 1645791 (Python Code)

Max Activating Token Index: 672

Text #17

Max Range: 0.5091. Min Range: -0.5091

Max Act: 0.3797. Min Act: -0.0002

Data Index: 1428683 (Python Code)

Max Activating Token Index: 413

Text #18

Max Range: 0.5091. Min Range: -0.5091

Max Act: 0.3805. Min Act: -0.0002

Data Index: 1638607 (Python Code)

Max Activating Token Index: 761

Text #19

Max Range: 0.5091. Min Range: -0.5091

Max Act: 0.3722. Min Act: -0.0002

Data Index: 1487278 (Python Code)

Max Activating Token Index: 737