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

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

Neuron 2583 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1359. Min Range: -0.1359

Max Act: 0.1359. Min Act: -0.0004

Data Index: 1640353 (Python Code)

Max Activating Token Index: 707

Text #1

Max Range: 0.1359. Min Range: -0.1359

Max Act: 0.1325. Min Act: -0.0004

Data Index: 1126899 (C4 (Web Text))

Max Activating Token Index: 528

Text #2

Max Range: 0.1359. Min Range: -0.1359

Max Act: 0.1064. Min Act: -0.0004

Data Index: 1393382 (Python Code)

Max Activating Token Index: 618

Text #3

Max Range: 0.1359. Min Range: -0.1359

Max Act: 0.1263. Min Act: -0.0004

Data Index: 1558392 (Python Code)

Max Activating Token Index: 351

Text #4

Max Range: 0.1359. Min Range: -0.1359

Max Act: 0.1257. Min Act: -0.0004

Data Index: 1365809 (Python Code)

Max Activating Token Index: 343

Text #5

Max Range: 0.1359. Min Range: -0.1359

Max Act: 0.1210. Min Act: -0.0004

Data Index: 1494276 (Python Code)

Max Activating Token Index: 307

Text #6

Max Range: 0.1359. Min Range: -0.1359

Max Act: 0.1202. Min Act: -0.0004

Data Index: 1413937 (Python Code)

Max Activating Token Index: 556

Text #7

Max Range: 0.1359. Min Range: -0.1359

Max Act: 0.1295. Min Act: -0.0004

Data Index: 1465301 (Python Code)

Max Activating Token Index: 774

Text #8

Max Range: 0.1359. Min Range: -0.1359

Max Act: 0.1338. Min Act: -0.0004

Data Index: 1438717 (Python Code)

Max Activating Token Index: 28

Text #9

Max Range: 0.1359. Min Range: -0.1359

Max Act: 0.1238. Min Act: -0.0004

Data Index: 1630794 (Python Code)

Max Activating Token Index: 47

Text #10

Max Range: 0.1359. Min Range: -0.1359

Max Act: 0.1277. Min Act: -0.0004

Data Index: 1363780 (Python Code)

Max Activating Token Index: 366

Text #11

Max Range: 0.1359. Min Range: -0.1359

Max Act: 0.1274. Min Act: -0.0004

Data Index: 1594120 (Python Code)

Max Activating Token Index: 415

Text #12

Max Range: 0.1359. Min Range: -0.1359

Max Act: 0.1132. Min Act: -0.0004

Data Index: 1567987 (Python Code)

Max Activating Token Index: 708

Text #13

Max Range: 0.1359. Min Range: -0.1359

Max Act: 0.1317. Min Act: -0.0004

Data Index: 1629769 (Python Code)

Max Activating Token Index: 22

Text #14

Max Range: 0.1359. Min Range: -0.1359

Max Act: 0.1268. Min Act: -0.0004

Data Index: 1565146 (Python Code)

Max Activating Token Index: 21

Text #15

Max Range: 0.1359. Min Range: -0.1359

Max Act: 0.1184. Min Act: -0.0004

Data Index: 1617220 (Python Code)

Max Activating Token Index: 291

Text #16

Max Range: 0.1359. Min Range: -0.1359

Max Act: 0.1266. Min Act: -0.0004

Data Index: 1529588 (Python Code)

Max Activating Token Index: 16

Text #17

Max Range: 0.1359. Min Range: -0.1359

Max Act: 0.1260. Min Act: -0.0004

Data Index: 1631843 (Python Code)

Max Activating Token Index: 778

Text #18

Max Range: 0.1359. Min Range: -0.1359

Max Act: 0.1256. Min Act: -0.0004

Data Index: 1541231 (Python Code)

Max Activating Token Index: 444

Text #19

Max Range: 0.1359. Min Range: -0.1359

Max Act: 0.1214. Min Act: -0.0004

Data Index: 1612075 (Python Code)

Max Activating Token Index: 11