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

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

Neuron 1873 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: 0.6846. Min Range: -0.6846

Max Act: 0.6846. Min Act: -0.0002

Data Index: 1497694 (Python Code)

Max Activating Token Index: 143

Text #1

Max Range: 0.6846. Min Range: -0.6846

Max Act: 0.6597. Min Act: -0.0002

Data Index: 1382264 (Python Code)

Max Activating Token Index: 345

Text #2

Max Range: 0.6846. Min Range: -0.6846

Max Act: 0.6402. Min Act: -0.0002

Data Index: 1596088 (Python Code)

Max Activating Token Index: 195

Text #3

Max Range: 0.6846. Min Range: -0.6846

Max Act: 0.6565. Min Act: -0.0002

Data Index: 1457926 (Python Code)

Max Activating Token Index: 115

Text #4

Max Range: 0.6846. Min Range: -0.6846

Max Act: 0.6507. Min Act: -0.0002

Data Index: 1619292 (Python Code)

Max Activating Token Index: 202

Text #5

Max Range: 0.6846. Min Range: -0.6846

Max Act: 0.6451. Min Act: -0.0002

Data Index: 1629015 (Python Code)

Max Activating Token Index: 92

Text #6

Max Range: 0.6846. Min Range: -0.6846

Max Act: 0.6376. Min Act: -0.0002

Data Index: 1388314 (Python Code)

Max Activating Token Index: 307

Text #7

Max Range: 0.6846. Min Range: -0.6846

Max Act: 0.6271. Min Act: -0.0002

Data Index: 1523083 (Python Code)

Max Activating Token Index: 120

Text #8

Max Range: 0.6846. Min Range: -0.6846

Max Act: 0.6260. Min Act: -0.0002

Data Index: 1506790 (Python Code)

Max Activating Token Index: 117

Text #9

Max Range: 0.6846. Min Range: -0.6846

Max Act: 0.6167. Min Act: -0.0002

Data Index: 1409419 (Python Code)

Max Activating Token Index: 530

Text #10

Max Range: 0.6846. Min Range: -0.6846

Max Act: 0.6350. Min Act: -0.0002

Data Index: 1477707 (Python Code)

Max Activating Token Index: 593

Text #11

Max Range: 0.6846. Min Range: -0.6846

Max Act: 0.6191. Min Act: -0.0002

Data Index: 1368887 (Python Code)

Max Activating Token Index: 439

Text #12

Max Range: 0.6846. Min Range: -0.6846

Max Act: 0.6218. Min Act: -0.0002

Data Index: 1576929 (Python Code)

Max Activating Token Index: 381

Text #13

Max Range: 0.6846. Min Range: -0.6846

Max Act: 0.6233. Min Act: -0.0002

Data Index: 1531720 (Python Code)

Max Activating Token Index: 139

Text #14

Max Range: 0.6846. Min Range: -0.6846

Max Act: 0.6200. Min Act: -0.0002

Data Index: 1378979 (Python Code)

Max Activating Token Index: 185

Text #15

Max Range: 0.6846. Min Range: -0.6846

Max Act: 0.6215. Min Act: -0.0002

Data Index: 1601935 (Python Code)

Max Activating Token Index: 687

Text #16

Max Range: 0.6846. Min Range: -0.6846

Max Act: 0.6136. Min Act: -0.0002

Data Index: 1405507 (Python Code)

Max Activating Token Index: 149

Text #17

Max Range: 0.6846. Min Range: -0.6846

Max Act: 0.6094. Min Act: -0.0002

Data Index: 1430828 (Python Code)

Max Activating Token Index: 208

Text #18

Max Range: 0.6846. Min Range: -0.6846

Max Act: 0.6192. Min Act: -0.0002

Data Index: 1362542 (Python Code)

Max Activating Token Index: 150

Text #19

Max Range: 0.6846. Min Range: -0.6846

Max Act: 0.6201. Min Act: -0.0002

Data Index: 1625526 (Python Code)

Max Activating Token Index: 326