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

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

Neuron 3121 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: 2.5244. Min Range: -2.5244

Max Act: 2.5244. Min Act: -0.0001

Data Index: 1624291 (Python Code)

Max Activating Token Index: 1023

Text #1

Max Range: 2.5244. Min Range: -2.5244

Max Act: 2.3992. Min Act: -0.0001

Data Index: 1528784 (Python Code)

Max Activating Token Index: 1023

Text #2

Max Range: 2.5244. Min Range: -2.5244

Max Act: 2.3479. Min Act: -0.0001

Data Index: 1580867 (Python Code)

Max Activating Token Index: 1023

Text #3

Max Range: 2.5244. Min Range: -2.5244

Max Act: 2.3260. Min Act: -0.0001

Data Index: 1415466 (Python Code)

Max Activating Token Index: 1023

Text #4

Max Range: 2.5244. Min Range: -2.5244

Max Act: 2.2861. Min Act: -0.0001

Data Index: 1465937 (Python Code)

Max Activating Token Index: 1023

Text #5

Max Range: 2.5244. Min Range: -2.5244

Max Act: 2.2802. Min Act: -0.0001

Data Index: 1645737 (Python Code)

Max Activating Token Index: 1023

Text #6

Max Range: 2.5244. Min Range: -2.5244

Max Act: 2.3009. Min Act: -0.0001

Data Index: 1634869 (Python Code)

Max Activating Token Index: 1023

Text #7

Max Range: 2.5244. Min Range: -2.5244

Max Act: 2.2934. Min Act: -0.0001

Data Index: 1616641 (Python Code)

Max Activating Token Index: 1023

Text #8

Max Range: 2.5244. Min Range: -2.5244

Max Act: 2.2741. Min Act: -0.0001

Data Index: 1386353 (Python Code)

Max Activating Token Index: 1023

Text #9

Max Range: 2.5244. Min Range: -2.5244

Max Act: 2.2682. Min Act: -0.0001

Data Index: 1644382 (Python Code)

Max Activating Token Index: 1023

Text #10

Max Range: 2.5244. Min Range: -2.5244

Max Act: 2.2647. Min Act: -0.0001

Data Index: 1430527 (Python Code)

Max Activating Token Index: 1023

Text #11

Max Range: 2.5244. Min Range: -2.5244

Max Act: 2.2528. Min Act: -0.0001

Data Index: 1580942 (Python Code)

Max Activating Token Index: 1023

Text #12

Max Range: 2.5244. Min Range: -2.5244

Max Act: 2.2716. Min Act: -0.0001

Data Index: 1397454 (Python Code)

Max Activating Token Index: 1023

Text #13

Max Range: 2.5244. Min Range: -2.5244

Max Act: 2.2703. Min Act: -0.0001

Data Index: 1651242 (Python Code)

Max Activating Token Index: 1023

Text #14

Max Range: 2.5244. Min Range: -2.5244

Max Act: 2.2561. Min Act: -0.0001

Data Index: 1495816 (Python Code)

Max Activating Token Index: 1023

Text #15

Max Range: 2.5244. Min Range: -2.5244

Max Act: 2.2361. Min Act: -0.0001

Data Index: 1465946 (Python Code)

Max Activating Token Index: 1023

Text #16

Max Range: 2.5244. Min Range: -2.5244

Max Act: 2.2695. Min Act: -0.0001

Data Index: 1420645 (Python Code)

Max Activating Token Index: 1023

Text #17

Max Range: 2.5244. Min Range: -2.5244

Max Act: 2.2285. Min Act: -0.0001

Data Index: 1633140 (Python Code)

Max Activating Token Index: 1023

Text #18

Max Range: 2.5244. Min Range: -2.5244

Max Act: 2.2412. Min Act: -0.0001

Data Index: 1567915 (Python Code)

Max Activating Token Index: 1023

Text #19

Max Range: 2.5244. Min Range: -2.5244

Max Act: 2.2337. Min Act: -0.0001

Data Index: 1443152 (Python Code)

Max Activating Token Index: 1023