Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2843 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1561. Min Range: -0.1561

Max Act: 0.1532. Min Act: -0.0001

Data Index: 1525203 (Python Code)

Max Activating Token Index: 643

Text #1

Max Range: 0.1561. Min Range: -0.1561

Max Act: 0.1561. Min Act: -0.0001

Data Index: 1635026 (Python Code)

Max Activating Token Index: 160

Text #2

Max Range: 0.1561. Min Range: -0.1561

Max Act: 0.1437. Min Act: -0.0001

Data Index: 1545951 (Python Code)

Max Activating Token Index: 817

Text #3

Max Range: 0.1561. Min Range: -0.1561

Max Act: 0.1346. Min Act: -0.0001

Data Index: 1525921 (Python Code)

Max Activating Token Index: 1012

Text #4

Max Range: 0.1561. Min Range: -0.1561

Max Act: 0.1274. Min Act: -0.0001

Data Index: 1422223 (Python Code)

Max Activating Token Index: 646

Text #5

Max Range: 0.1561. Min Range: -0.1561

Max Act: 0.1222. Min Act: -0.0001

Data Index: 1484785 (Python Code)

Max Activating Token Index: 287

Text #6

Max Range: 0.1561. Min Range: -0.1561

Max Act: 0.1317. Min Act: -0.0001

Data Index: 1556800 (Python Code)

Max Activating Token Index: 285

Text #7

Max Range: 0.1561. Min Range: -0.1561

Max Act: 0.1276. Min Act: -0.0001

Data Index: 1536826 (Python Code)

Max Activating Token Index: 162

Text #8

Max Range: 0.1561. Min Range: -0.1561

Max Act: 0.1210. Min Act: -0.0001

Data Index: 1561286 (Python Code)

Max Activating Token Index: 876

Text #9

Max Range: 0.1561. Min Range: -0.1561

Max Act: 0.1302. Min Act: -0.0001

Data Index: 1391148 (Python Code)

Max Activating Token Index: 289

Text #10

Max Range: 0.1561. Min Range: -0.1561

Max Act: 0.1201. Min Act: -0.0001

Data Index: 1414425 (Python Code)

Max Activating Token Index: 850

Text #11

Max Range: 0.1561. Min Range: -0.1561

Max Act: 0.1197. Min Act: -0.0001

Data Index: 1542742 (Python Code)

Max Activating Token Index: 295

Text #12

Max Range: 0.1561. Min Range: -0.1561

Max Act: 0.1292. Min Act: -0.0001

Data Index: 1386600 (Python Code)

Max Activating Token Index: 583

Text #13

Max Range: 0.1561. Min Range: -0.1561

Max Act: 0.1162. Min Act: -0.0001

Data Index: 1527240 (Python Code)

Max Activating Token Index: 759

Text #14

Max Range: 0.1561. Min Range: -0.1561

Max Act: 0.1198. Min Act: -0.0001

Data Index: 1400947 (Python Code)

Max Activating Token Index: 123

Text #15

Max Range: 0.1561. Min Range: -0.1561

Max Act: 0.1145. Min Act: -0.0001

Data Index: 1612852 (Python Code)

Max Activating Token Index: 161

Text #16

Max Range: 0.1561. Min Range: -0.1561

Max Act: 0.1261. Min Act: -0.0001

Data Index: 1420885 (Python Code)

Max Activating Token Index: 798

Text #17

Max Range: 0.1561. Min Range: -0.1561

Max Act: 0.1169. Min Act: -0.0001

Data Index: 1405362 (Python Code)

Max Activating Token Index: 476

Text #18

Max Range: 0.1561. Min Range: -0.1561

Max Act: 0.1154. Min Act: -0.0001

Data Index: 1527537 (Python Code)

Max Activating Token Index: 399

Text #19

Max Range: 0.1561. Min Range: -0.1561

Max Act: 0.1193. Min Act: -0.0001

Data Index: 1610779 (Python Code)

Max Activating Token Index: 90