Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3142 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 3.6270. Min Range: -3.6270
Max Act: 3.6270. Min Act: -0.0001
Data Index: 1419941 (Python Code)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6270. Min Range: -3.6270
Max Act: 3.4301. Min Act: -0.0001
Data Index: 1492093 (Python Code)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6270. Min Range: -3.6270
Max Act: 3.0335. Min Act: -0.0001
Data Index: 1441900 (Python Code)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6270. Min Range: -3.6270
Max Act: 3.1350. Min Act: -0.0001
Data Index: 1640916 (Python Code)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6270. Min Range: -3.6270
Max Act: 2.8746. Min Act: -0.0001
Data Index: 1590632 (Python Code)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6270. Min Range: -3.6270
Max Act: 2.6640. Min Act: -0.0001
Data Index: 1417272 (Python Code)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6270. Min Range: -3.6270
Max Act: 2.9426. Min Act: -0.0001
Data Index: 1486644 (Python Code)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6270. Min Range: -3.6270
Max Act: 2.9425. Min Act: -0.0001
Data Index: 1440396 (Python Code)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6270. Min Range: -3.6270
Max Act: 2.9181. Min Act: -0.0001
Data Index: 1453186 (Python Code)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6270. Min Range: -3.6270
Max Act: 3.0657. Min Act: -0.0001
Data Index: 1513283 (Python Code)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6270. Min Range: -3.6270
Max Act: 2.9111. Min Act: -0.0001
Data Index: 1404436 (Python Code)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6270. Min Range: -3.6270
Max Act: 2.8833. Min Act: -0.0001
Data Index: 1391560 (Python Code)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6270. Min Range: -3.6270
Max Act: 2.5778. Min Act: -0.0001
Data Index: 1431255 (Python Code)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6270. Min Range: -3.6270
Max Act: 2.8161. Min Act: -0.0001
Data Index: 1441068 (Python Code)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6270. Min Range: -3.6270
Max Act: 2.6533. Min Act: -0.0001
Data Index: 1642734 (Python Code)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6270. Min Range: -3.6270
Max Act: 2.6502. Min Act: -0.0001
Data Index: 1555062 (Python Code)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6270. Min Range: -3.6270
Max Act: 2.7873. Min Act: -0.0001
Data Index: 1434039 (Python Code)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6270. Min Range: -3.6270
Max Act: 2.3623. Min Act: -0.0001
Data Index: 1410765 (Python Code)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6270. Min Range: -3.6270
Max Act: 2.6493. Min Act: -0.0001
Data Index: 1422428 (Python Code)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6270. Min Range: -3.6270
Max Act: 2.4901. Min Act: -0.0001
Data Index: 1650230 (Python Code)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #19