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

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

Neuron 906 in Layer 0

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: 0.9278. Min Range: -0.9278

Max Act: 0.9099. Min Act: -0.0001

Data Index: 1613530 (Python Code)

Max Activating Token Index: 1023

Text #1

Max Range: 0.9278. Min Range: -0.9278

Max Act: 0.9044. Min Act: -0.0001

Data Index: 1628160 (Python Code)

Max Activating Token Index: 1023

Text #2

Max Range: 0.9278. Min Range: -0.9278

Max Act: 0.9278. Min Act: -0.0001

Data Index: 1436350 (Python Code)

Max Activating Token Index: 1023

Text #3

Max Range: 0.9278. Min Range: -0.9278

Max Act: 0.8818. Min Act: -0.0001

Data Index: 1449584 (Python Code)

Max Activating Token Index: 1023

Text #4

Max Range: 0.9278. Min Range: -0.9278

Max Act: 0.8618. Min Act: -0.0001

Data Index: 1607776 (Python Code)

Max Activating Token Index: 5

Text #5

Max Range: 0.9278. Min Range: -0.9278

Max Act: 0.8266. Min Act: -0.0002

Data Index: 1465941 (Python Code)

Max Activating Token Index: 1023

Text #6

Max Range: 0.9278. Min Range: -0.9278

Max Act: 0.8094. Min Act: -0.0001

Data Index: 1373855 (Python Code)

Max Activating Token Index: 1023

Text #7

Max Range: 0.9278. Min Range: -0.9278

Max Act: 0.8063. Min Act: -0.0002

Data Index: 1420654 (Python Code)

Max Activating Token Index: 1023

Text #8

Max Range: 0.9278. Min Range: -0.9278

Max Act: 0.7848. Min Act: -0.0001

Data Index: 1599058 (Python Code)

Max Activating Token Index: 44

Text #9

Max Range: 0.9278. Min Range: -0.9278

Max Act: 0.7676. Min Act: -0.0002

Data Index: 1595115 (Python Code)

Max Activating Token Index: 1023

Text #10

Max Range: 0.9278. Min Range: -0.9278

Max Act: 0.7583. Min Act: -0.0001

Data Index: 1385559 (Python Code)

Max Activating Token Index: 1023

Text #11

Max Range: 0.9278. Min Range: -0.9278

Max Act: 0.7470. Min Act: -0.0002

Data Index: 1550510 (Python Code)

Max Activating Token Index: 1023

Text #12

Max Range: 0.9278. Min Range: -0.9278

Max Act: 0.7556. Min Act: -0.0001

Data Index: 1410181 (Python Code)

Max Activating Token Index: 20

Text #13

Max Range: 0.9278. Min Range: -0.9278

Max Act: 0.7559. Min Act: -0.0001

Data Index: 1412901 (Python Code)

Max Activating Token Index: 41

Text #14

Max Range: 0.9278. Min Range: -0.9278

Max Act: 0.7498. Min Act: -0.0001

Data Index: 1590173 (Python Code)

Max Activating Token Index: 1023

Text #15

Max Range: 0.9278. Min Range: -0.9278

Max Act: 0.7326. Min Act: -0.0001

Data Index: 1537341 (Python Code)

Max Activating Token Index: 43

Text #16

Max Range: 0.9278. Min Range: -0.9278

Max Act: 0.7353. Min Act: -0.0001

Data Index: 1376596 (Python Code)

Max Activating Token Index: 203

Text #17

Max Range: 0.9278. Min Range: -0.9278

Max Act: 0.7311. Min Act: -0.0001

Data Index: 1650520 (Python Code)

Max Activating Token Index: 5

Text #18

Max Range: 0.9278. Min Range: -0.9278

Max Act: 0.7277. Min Act: -0.0001

Data Index: 1390337 (Python Code)

Max Activating Token Index: 1023

Text #19

Max Range: 0.9278. Min Range: -0.9278

Max Act: 0.7207. Min Act: -0.0002

Data Index: 1423854 (Python Code)

Max Activating Token Index: 19