Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1984 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 5.2187. Min Range: -5.2187
Max Act: 5.2187. Min Act: -0.1700
Data Index: 1408371 (Python Code)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2187. Min Range: -5.2187
Max Act: 5.0312. Min Act: -0.1700
Data Index: 257375 (C4 (Web Text))
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2187. Min Range: -5.2187
Max Act: 5.0625. Min Act: -0.1700
Data Index: 1375739 (Python Code)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2187. Min Range: -5.2187
Max Act: 5.0000. Min Act: -0.1700
Data Index: 1435575 (Python Code)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2187. Min Range: -5.2187
Max Act: 5.0000. Min Act: -0.1700
Data Index: 1413456 (Python Code)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2187. Min Range: -5.2187
Max Act: 5.0000. Min Act: -0.1700
Data Index: 1421321 (Python Code)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2187. Min Range: -5.2187
Max Act: 4.9687. Min Act: -0.1700
Data Index: 1556580 (Python Code)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2187. Min Range: -5.2187
Max Act: 4.9375. Min Act: -0.1700
Data Index: 1275544 (C4 (Web Text))
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2187. Min Range: -5.2187
Max Act: 4.9687. Min Act: -0.1700
Data Index: 1637769 (Python Code)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2187. Min Range: -5.2187
Max Act: 4.8125. Min Act: -0.1700
Data Index: 1528895 (Python Code)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2187. Min Range: -5.2187
Max Act: 4.9062. Min Act: -0.1700
Data Index: 1639828 (Python Code)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2187. Min Range: -5.2187
Max Act: 4.9375. Min Act: -0.1700
Data Index: 1471546 (Python Code)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2187. Min Range: -5.2187
Max Act: 4.9062. Min Act: -0.1700
Data Index: 1375635 (Python Code)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2187. Min Range: -5.2187
Max Act: 4.9375. Min Act: -0.1700
Data Index: 1499679 (Python Code)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2187. Min Range: -5.2187
Max Act: 4.8750. Min Act: -0.1700
Data Index: 899541 (C4 (Web Text))
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2187. Min Range: -5.2187
Max Act: 4.9375. Min Act: -0.1700
Data Index: 1485521 (Python Code)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2187. Min Range: -5.2187
Max Act: 4.8437. Min Act: -0.1700
Data Index: 1481284 (Python Code)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2187. Min Range: -5.2187
Max Act: 4.9062. Min Act: -0.1700
Data Index: 1438772 (Python Code)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2187. Min Range: -5.2187
Max Act: 4.8437. Min Act: -0.1700
Data Index: 1398617 (Python Code)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2187. Min Range: -5.2187
Max Act: 4.7500. Min Act: -0.1700
Data Index: 1600781 (Python Code)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #19