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

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

Neuron 5981 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: 0.1358. Min Range: -0.1358

Max Act: 0.1358. Min Act: -0.0002

Data Index: 1535156 (Python Code)

Max Activating Token Index: 118

Text #1

Max Range: 0.1358. Min Range: -0.1358

Max Act: 0.1351. Min Act: -0.0002

Data Index: 1589010 (Python Code)

Max Activating Token Index: 559

Text #2

Max Range: 0.1358. Min Range: -0.1358

Max Act: 0.1342. Min Act: -0.0002

Data Index: 1497427 (Python Code)

Max Activating Token Index: 45

Text #3

Max Range: 0.1358. Min Range: -0.1358

Max Act: 0.1310. Min Act: -0.0002

Data Index: 1567565 (Python Code)

Max Activating Token Index: 95

Text #4

Max Range: 0.1358. Min Range: -0.1358

Max Act: 0.1298. Min Act: -0.0002

Data Index: 1451403 (Python Code)

Max Activating Token Index: 44

Text #5

Max Range: 0.1358. Min Range: -0.1358

Max Act: 0.1295. Min Act: -0.0002

Data Index: 1368156 (Python Code)

Max Activating Token Index: 40

Text #6

Max Range: 0.1358. Min Range: -0.1358

Max Act: 0.1278. Min Act: -0.0002

Data Index: 1553354 (Python Code)

Max Activating Token Index: 46

Text #7

Max Range: 0.1358. Min Range: -0.1358

Max Act: 0.1261. Min Act: -0.0002

Data Index: 1439301 (Python Code)

Max Activating Token Index: 179

Text #8

Max Range: 0.1358. Min Range: -0.1358

Max Act: 0.1255. Min Act: -0.0002

Data Index: 1509061 (Python Code)

Max Activating Token Index: 123

Text #9

Max Range: 0.1358. Min Range: -0.1358

Max Act: 0.1262. Min Act: -0.0002

Data Index: 1597830 (Python Code)

Max Activating Token Index: 57

Text #10

Max Range: 0.1358. Min Range: -0.1358

Max Act: 0.1251. Min Act: -0.0002

Data Index: 1574347 (Python Code)

Max Activating Token Index: 192

Text #11

Max Range: 0.1358. Min Range: -0.1358

Max Act: 0.1243. Min Act: -0.0002

Data Index: 1501372 (Python Code)

Max Activating Token Index: 192

Text #12

Max Range: 0.1358. Min Range: -0.1358

Max Act: 0.1236. Min Act: -0.0002

Data Index: 1596646 (Python Code)

Max Activating Token Index: 242

Text #13

Max Range: 0.1358. Min Range: -0.1358

Max Act: 0.1223. Min Act: -0.0002

Data Index: 1533820 (Python Code)

Max Activating Token Index: 311

Text #14

Max Range: 0.1358. Min Range: -0.1358

Max Act: 0.1231. Min Act: -0.0002

Data Index: 1461848 (Python Code)

Max Activating Token Index: 201

Text #15

Max Range: 0.1358. Min Range: -0.1358

Max Act: 0.1225. Min Act: -0.0002

Data Index: 1410515 (Python Code)

Max Activating Token Index: 35

Text #16

Max Range: 0.1358. Min Range: -0.1358

Max Act: 0.1198. Min Act: -0.0002

Data Index: 1656186 (Python Code)

Max Activating Token Index: 131

Text #17

Max Range: 0.1358. Min Range: -0.1358

Max Act: 0.1174. Min Act: -0.0002

Data Index: 1389015 (Python Code)

Max Activating Token Index: 246

Text #18

Max Range: 0.1358. Min Range: -0.1358

Max Act: 0.1192. Min Act: -0.0002

Data Index: 1564579 (Python Code)

Max Activating Token Index: 982

Text #19

Max Range: 0.1358. Min Range: -0.1358

Max Act: 0.1139. Min Act: -0.0002

Data Index: 1400366 (Python Code)

Max Activating Token Index: 127