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

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

Neuron 4402 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: 2.1231. Min Range: -2.1231

Max Act: 2.1231. Min Act: -0.0001

Data Index: 1571082 (Python Code)

Max Activating Token Index: 57

Text #1

Max Range: 2.1231. Min Range: -2.1231

Max Act: 1.9963. Min Act: -0.0001

Data Index: 1439595 (Python Code)

Max Activating Token Index: 1023

Text #2

Max Range: 2.1231. Min Range: -2.1231

Max Act: 1.9650. Min Act: -0.0001

Data Index: 1527454 (Python Code)

Max Activating Token Index: 1023

Text #3

Max Range: 2.1231. Min Range: -2.1231

Max Act: 1.9539. Min Act: -0.0001

Data Index: 1410491 (Python Code)

Max Activating Token Index: 88

Text #4

Max Range: 2.1231. Min Range: -2.1231

Max Act: 1.9798. Min Act: -0.0002

Data Index: 1655293 (Python Code)

Max Activating Token Index: 40

Text #5

Max Range: 2.1231. Min Range: -2.1231

Max Act: 1.9460. Min Act: -0.0001

Data Index: 1507754 (Python Code)

Max Activating Token Index: 31

Text #6

Max Range: 2.1231. Min Range: -2.1231

Max Act: 1.9582. Min Act: -0.0001

Data Index: 1517834 (Python Code)

Max Activating Token Index: 42

Text #7

Max Range: 2.1231. Min Range: -2.1231

Max Act: 1.9716. Min Act: -0.0001

Data Index: 1552945 (Python Code)

Max Activating Token Index: 88

Text #8

Max Range: 2.1231. Min Range: -2.1231

Max Act: 1.9492. Min Act: -0.0001

Data Index: 1404735 (Python Code)

Max Activating Token Index: 1023

Text #9

Max Range: 2.1231. Min Range: -2.1231

Max Act: 1.9424. Min Act: -0.0001

Data Index: 1628698 (Python Code)

Max Activating Token Index: 15

Text #10

Max Range: 2.1231. Min Range: -2.1231

Max Act: 1.9239. Min Act: -0.0001

Data Index: 1457223 (Python Code)

Max Activating Token Index: 51

Text #11

Max Range: 2.1231. Min Range: -2.1231

Max Act: 1.9308. Min Act: -0.0001

Data Index: 1564608 (Python Code)

Max Activating Token Index: 11

Text #12

Max Range: 2.1231. Min Range: -2.1231

Max Act: 1.9442. Min Act: -0.0001

Data Index: 1389172 (Python Code)

Max Activating Token Index: 25

Text #13

Max Range: 2.1231. Min Range: -2.1231

Max Act: 1.9227. Min Act: -0.0001

Data Index: 1386005 (Python Code)

Max Activating Token Index: 84

Text #14

Max Range: 2.1231. Min Range: -2.1231

Max Act: 1.9295. Min Act: -0.0001

Data Index: 1615798 (Python Code)

Max Activating Token Index: 1023

Text #15

Max Range: 2.1231. Min Range: -2.1231

Max Act: 1.9401. Min Act: -0.0001

Data Index: 1441251 (Python Code)

Max Activating Token Index: 1023

Text #16

Max Range: 2.1231. Min Range: -2.1231

Max Act: 1.9578. Min Act: -0.0001

Data Index: 1604917 (Python Code)

Max Activating Token Index: 13

Text #17

Max Range: 2.1231. Min Range: -2.1231

Max Act: 1.9100. Min Act: -0.0001

Data Index: 1633206 (Python Code)

Max Activating Token Index: 62

Text #18

Max Range: 2.1231. Min Range: -2.1231

Max Act: 1.9335. Min Act: -0.0001

Data Index: 1629593 (Python Code)

Max Activating Token Index: 28

Text #19

Max Range: 2.1231. Min Range: -2.1231

Max Act: 1.9172. Min Act: -0.0001

Data Index: 1458609 (Python Code)

Max Activating Token Index: 25