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

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

Neuron 5204 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: 0.0320. Min Range: -0.0320

Max Act: 0.0320. Min Act: -0.0001

Data Index: 1366640 (Python Code)

Max Activating Token Index: 952

Text #1

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0278. Min Act: -0.0001

Data Index: 1595436 (Python Code)

Max Activating Token Index: 1

Text #2

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0257. Min Act: -0.0001

Data Index: 1540291 (Python Code)

Max Activating Token Index: 936

Text #3

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0249. Min Act: -0.0001

Data Index: 1498414 (Python Code)

Max Activating Token Index: 841

Text #4

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0241. Min Act: -0.0001

Data Index: 150527 (C4 (Web Text))

Max Activating Token Index: 15

Text #5

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0229. Min Act: -0.0001

Data Index: 1589300 (Python Code)

Max Activating Token Index: 2

Text #6

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0228. Min Act: -0.0001

Data Index: 575765 (C4 (Web Text))

Max Activating Token Index: 497

Text #7

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0231. Min Act: -0.0001

Data Index: 1421193 (Python Code)

Max Activating Token Index: 602

Text #8

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0224. Min Act: -0.0001

Data Index: 1596104 (Python Code)

Max Activating Token Index: 14

Text #9

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0220. Min Act: -0.0001

Data Index: 1361627 (Python Code)

Max Activating Token Index: 22

Text #10

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0222. Min Act: -0.0001

Data Index: 1503643 (Python Code)

Max Activating Token Index: 35

Text #11

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0218. Min Act: -0.0001

Data Index: 1596557 (Python Code)

Max Activating Token Index: 155

Text #12

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0221. Min Act: -0.0001

Data Index: 1398542 (Python Code)

Max Activating Token Index: 18

Text #13

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0220. Min Act: -0.0001

Data Index: 1374969 (Python Code)

Max Activating Token Index: 419

Text #14

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0212. Min Act: -0.0001

Data Index: 1486541 (Python Code)

Max Activating Token Index: 634

Text #15

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0217. Min Act: -0.0001

Data Index: 1448404 (Python Code)

Max Activating Token Index: 631

Text #16

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0217. Min Act: -0.0001

Data Index: 1641960 (Python Code)

Max Activating Token Index: 105

Text #17

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0213. Min Act: -0.0001

Data Index: 1412802 (Python Code)

Max Activating Token Index: 2

Text #18

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0210. Min Act: -0.0002

Data Index: 1456105 (Python Code)

Max Activating Token Index: 284

Text #19

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0208. Min Act: -0.0001

Data Index: 1614279 (Python Code)

Max Activating Token Index: 589