Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1986 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 4.1677. Min Range: -4.1677
Max Act: 4.1677. Min Act: -0.1700
Data Index: 1481914 (Python Code)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1677. Min Range: -4.1677
Max Act: 4.0739. Min Act: -0.1700
Data Index: 1613076 (Python Code)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1677. Min Range: -4.1677
Max Act: 4.1052. Min Act: -0.1700
Data Index: 1536386 (Python Code)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1677. Min Range: -4.1677
Max Act: 4.0426. Min Act: -0.1700
Data Index: 1586414 (Python Code)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1677. Min Range: -4.1677
Max Act: 4.0114. Min Act: -0.1700
Data Index: 1409015 (Python Code)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1677. Min Range: -4.1677
Max Act: 4.0114. Min Act: -0.1700
Data Index: 1435787 (Python Code)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1677. Min Range: -4.1677
Max Act: 3.9176. Min Act: -0.1700
Data Index: 1360904 (Python Code)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1677. Min Range: -4.1677
Max Act: 3.9176. Min Act: -0.1700
Data Index: 1370930 (Python Code)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1677. Min Range: -4.1677
Max Act: 3.9176. Min Act: -0.1700
Data Index: 1427126 (Python Code)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1677. Min Range: -4.1677
Max Act: 3.9488. Min Act: -0.1700
Data Index: 1503247 (Python Code)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1677. Min Range: -4.1677
Max Act: 3.8863. Min Act: -0.1700
Data Index: 1558999 (Python Code)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1677. Min Range: -4.1677
Max Act: 3.8863. Min Act: -0.1700
Data Index: 1607406 (Python Code)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1677. Min Range: -4.1677
Max Act: 3.8550. Min Act: -0.1700
Data Index: 1385912 (Python Code)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1677. Min Range: -4.1677
Max Act: 3.8863. Min Act: -0.1700
Data Index: 1540513 (Python Code)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1677. Min Range: -4.1677
Max Act: 3.8863. Min Act: -0.1700
Data Index: 1650906 (Python Code)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1677. Min Range: -4.1677
Max Act: 3.8550. Min Act: -0.1700
Data Index: 1505749 (Python Code)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1677. Min Range: -4.1677
Max Act: 3.9488. Min Act: -0.1700
Data Index: 1597968 (Python Code)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1677. Min Range: -4.1677
Max Act: 3.8237. Min Act: -0.1700
Data Index: 1563625 (Python Code)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1677. Min Range: -4.1677
Max Act: 3.7925. Min Act: -0.1700
Data Index: 1500308 (Python Code)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1677. Min Range: -4.1677
Max Act: 3.8081. Min Act: -0.1700
Data Index: 1538483 (Python Code)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #19