Model: SoLU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 323 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')
Text #0
Max Range: 0.1803. Min Range: -0.1803
Max Act: 0.1803. Min Act: -0.0005
Data Index: 1008188 (C4 (Web Text))
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.1803. Min Range: -0.1803
Max Act: 0.1764. Min Act: -0.0006
Data Index: 825576 (C4 (Web Text))
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.1803. Min Range: -0.1803
Max Act: 0.1724. Min Act: -0.0006
Data Index: 782003 (C4 (Web Text))
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.1803. Min Range: -0.1803
Max Act: 0.1468. Min Act: -0.0006
Data Index: 143588 (C4 (Web Text))
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.1803. Min Range: -0.1803
Max Act: 0.1523. Min Act: -0.0006
Data Index: 646903 (C4 (Web Text))
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.1803. Min Range: -0.1803
Max Act: 0.1412. Min Act: -0.0006
Data Index: 1176460 (C4 (Web Text))
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.1803. Min Range: -0.1803
Max Act: 0.1341. Min Act: -0.0006
Data Index: 596795 (C4 (Web Text))
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.1803. Min Range: -0.1803
Max Act: 0.1334. Min Act: -0.0006
Data Index: 1030636 (C4 (Web Text))
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.1803. Min Range: -0.1803
Max Act: 0.1388. Min Act: -0.0006
Data Index: 730495 (C4 (Web Text))
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.1803. Min Range: -0.1803
Max Act: 0.1331. Min Act: -0.0006
Data Index: 884677 (C4 (Web Text))
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.1803. Min Range: -0.1803
Max Act: 0.1317. Min Act: -0.0006
Data Index: 218089 (C4 (Web Text))
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.1803. Min Range: -0.1803
Max Act: 0.1268. Min Act: -0.0006
Data Index: 730214 (C4 (Web Text))
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.1803. Min Range: -0.1803
Max Act: 0.1360. Min Act: -0.0006
Data Index: 18685 (C4 (Web Text))
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.1803. Min Range: -0.1803
Max Act: 0.1407. Min Act: -0.0006
Data Index: 826918 (C4 (Web Text))
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.1803. Min Range: -0.1803
Max Act: 0.1344. Min Act: -0.0006
Data Index: 1185830 (C4 (Web Text))
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.1803. Min Range: -0.1803
Max Act: 0.1289. Min Act: -0.0006
Data Index: 974381 (C4 (Web Text))
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.1803. Min Range: -0.1803
Max Act: 0.1264. Min Act: -0.0006
Data Index: 242847 (C4 (Web Text))
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.1803. Min Range: -0.1803
Max Act: 0.1257. Min Act: -0.0006
Data Index: 1460727 (Python Code)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.1803. Min Range: -0.1803
Max Act: 0.1161. Min Act: -0.0006
Data Index: 1047568 (C4 (Web Text))
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.1803. Min Range: -0.1803
Max Act: 0.1243. Min Act: -0.0006
Data Index: 1607963 (Python Code)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #19