Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3543 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 0.2166. Min Range: -0.2166
Max Act: 0.2166. Min Act: -0.0001
Data Index: 1505223 (Python Code)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.2166. Min Range: -0.2166
Max Act: 0.1901. Min Act: -0.0001
Data Index: 1417368 (Python Code)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.2166. Min Range: -0.2166
Max Act: 0.1775. Min Act: -0.0001
Data Index: 1435912 (Python Code)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.2166. Min Range: -0.2166
Max Act: 0.1715. Min Act: -0.0001
Data Index: 1397837 (Python Code)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.2166. Min Range: -0.2166
Max Act: 0.1738. Min Act: -0.0001
Data Index: 1608006 (Python Code)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.2166. Min Range: -0.2166
Max Act: 0.1371. Min Act: -0.0001
Data Index: 1586540 (Python Code)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.2166. Min Range: -0.2166
Max Act: 0.1389. Min Act: -0.0001
Data Index: 1633453 (Python Code)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.2166. Min Range: -0.2166
Max Act: 0.1327. Min Act: -0.0001
Data Index: 1546270 (Python Code)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.2166. Min Range: -0.2166
Max Act: 0.1361. Min Act: -0.0001
Data Index: 1596538 (Python Code)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.2166. Min Range: -0.2166
Max Act: 0.1296. Min Act: -0.0001
Data Index: 1617321 (Python Code)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.2166. Min Range: -0.2166
Max Act: 0.1368. Min Act: -0.0001
Data Index: 1473012 (Python Code)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.2166. Min Range: -0.2166
Max Act: 0.1276. Min Act: -0.0001
Data Index: 1422415 (Python Code)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.2166. Min Range: -0.2166
Max Act: 0.1184. Min Act: -0.0001
Data Index: 1396142 (Python Code)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.2166. Min Range: -0.2166
Max Act: 0.1224. Min Act: -0.0001
Data Index: 1521385 (Python Code)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.2166. Min Range: -0.2166
Max Act: 0.1197. Min Act: -0.0001
Data Index: 1645550 (Python Code)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.2166. Min Range: -0.2166
Max Act: 0.1184. Min Act: -0.0001
Data Index: 1555338 (Python Code)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.2166. Min Range: -0.2166
Max Act: 0.1178. Min Act: -0.0001
Data Index: 1573725 (Python Code)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.2166. Min Range: -0.2166
Max Act: 0.1211. Min Act: -0.0001
Data Index: 1604980 (Python Code)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.2166. Min Range: -0.2166
Max Act: 0.1110. Min Act: -0.0001
Data Index: 766177 (C4 (Web Text))
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.2166. Min Range: -0.2166
Max Act: 0.1147. Min Act: -0.0001
Data Index: 1455459 (Python Code)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #19