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

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

Neuron 5809 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: 0.8854. Min Range: -0.8854

Max Act: 0.8854. Min Act: -0.0002

Data Index: 1539412 (Python Code)

Max Activating Token Index: 326

Text #1

Max Range: 0.8854. Min Range: -0.8854

Max Act: 0.8597. Min Act: -0.0002

Data Index: 1426774 (Python Code)

Max Activating Token Index: 6

Text #2

Max Range: 0.8854. Min Range: -0.8854

Max Act: 0.8773. Min Act: -0.0002

Data Index: 1542444 (Python Code)

Max Activating Token Index: 794

Text #3

Max Range: 0.8854. Min Range: -0.8854

Max Act: 0.8381. Min Act: -0.0002

Data Index: 1546208 (Python Code)

Max Activating Token Index: 51

Text #4

Max Range: 0.8854. Min Range: -0.8854

Max Act: 0.8235. Min Act: -0.0002

Data Index: 1374433 (Python Code)

Max Activating Token Index: 460

Text #5

Max Range: 0.8854. Min Range: -0.8854

Max Act: 0.8005. Min Act: -0.0002

Data Index: 1614864 (Python Code)

Max Activating Token Index: 25

Text #6

Max Range: 0.8854. Min Range: -0.8854

Max Act: 0.7852. Min Act: -0.0002

Data Index: 1626747 (Python Code)

Max Activating Token Index: 179

Text #7

Max Range: 0.8854. Min Range: -0.8854

Max Act: 0.7895. Min Act: -0.0002

Data Index: 1525453 (Python Code)

Max Activating Token Index: 231

Text #8

Max Range: 0.8854. Min Range: -0.8854

Max Act: 0.7935. Min Act: -0.0002

Data Index: 1609950 (Python Code)

Max Activating Token Index: 287

Text #9

Max Range: 0.8854. Min Range: -0.8854

Max Act: 0.7844. Min Act: -0.0002

Data Index: 1418515 (Python Code)

Max Activating Token Index: 7

Text #10

Max Range: 0.8854. Min Range: -0.8854

Max Act: 0.7754. Min Act: -0.0002

Data Index: 1406505 (Python Code)

Max Activating Token Index: 1015

Text #11

Max Range: 0.8854. Min Range: -0.8854

Max Act: 0.7658. Min Act: -0.0002

Data Index: 1470541 (Python Code)

Max Activating Token Index: 315

Text #12

Max Range: 0.8854. Min Range: -0.8854

Max Act: 0.7730. Min Act: -0.0002

Data Index: 1381888 (Python Code)

Max Activating Token Index: 19

Text #13

Max Range: 0.8854. Min Range: -0.8854

Max Act: 0.7491. Min Act: -0.0002

Data Index: 1655781 (Python Code)

Max Activating Token Index: 1008

Text #14

Max Range: 0.8854. Min Range: -0.8854

Max Act: 0.7633. Min Act: -0.0002

Data Index: 1489040 (Python Code)

Max Activating Token Index: 996

Text #15

Max Range: 0.8854. Min Range: -0.8854

Max Act: 0.7512. Min Act: -0.0002

Data Index: 1381485 (Python Code)

Max Activating Token Index: 45

Text #16

Max Range: 0.8854. Min Range: -0.8854

Max Act: 0.7449. Min Act: -0.0002

Data Index: 1566430 (Python Code)

Max Activating Token Index: 951

Text #17

Max Range: 0.8854. Min Range: -0.8854

Max Act: 0.7476. Min Act: -0.0002

Data Index: 1401541 (Python Code)

Max Activating Token Index: 51

Text #18

Max Range: 0.8854. Min Range: -0.8854

Max Act: 0.7392. Min Act: -0.0002

Data Index: 1417480 (Python Code)

Max Activating Token Index: 863

Text #19

Max Range: 0.8854. Min Range: -0.8854

Max Act: 0.7328. Min Act: -0.0002

Data Index: 1535870 (Python Code)

Max Activating Token Index: 11