Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3958 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.9071. Min Range: -6.9071
Max Act: 6.9071. Min Act: -0.1700
Data Index: 7015129 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9071. Min Range: -6.9071
Max Act: 6.8759. Min Act: -0.1700
Data Index: 3059600 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9071. Min Range: -6.9071
Max Act: 6.8446. Min Act: -0.1700
Data Index: 6668240 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9071. Min Range: -6.9071
Max Act: 6.7821. Min Act: -0.1700
Data Index: 7015971 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9071. Min Range: -6.9071
Max Act: 6.7821. Min Act: -0.1700
Data Index: 5463733 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9071. Min Range: -6.9071
Max Act: 6.8134. Min Act: -0.1700
Data Index: 7842115 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9071. Min Range: -6.9071
Max Act: 6.7821. Min Act: -0.1700
Data Index: 5567092 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9071. Min Range: -6.9071
Max Act: 6.7509. Min Act: -0.1700
Data Index: 7750788 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9071. Min Range: -6.9071
Max Act: 6.7196. Min Act: -0.1700
Data Index: 7473844 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9071. Min Range: -6.9071
Max Act: 6.6884. Min Act: -0.1700
Data Index: 8458351 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9071. Min Range: -6.9071
Max Act: 6.6884. Min Act: -0.1700
Data Index: 1297771 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9071. Min Range: -6.9071
Max Act: 6.6571. Min Act: -0.1700
Data Index: 5308132 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9071. Min Range: -6.9071
Max Act: 6.6884. Min Act: -0.1700
Data Index: 6632359 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9071. Min Range: -6.9071
Max Act: 6.6259. Min Act: -0.1700
Data Index: 3641659 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9071. Min Range: -6.9071
Max Act: 6.6259. Min Act: -0.1700
Data Index: 5455082 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9071. Min Range: -6.9071
Max Act: 6.6884. Min Act: -0.1700
Data Index: 4517368 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9071. Min Range: -6.9071
Max Act: 6.6884. Min Act: -0.1700
Data Index: 1019191 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9071. Min Range: -6.9071
Max Act: 6.5946. Min Act: -0.1700
Data Index: 2093650 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9071. Min Range: -6.9071
Max Act: 6.6571. Min Act: -0.1700
Data Index: 6282803 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9071. Min Range: -6.9071
Max Act: 6.5946. Min Act: -0.1700
Data Index: 6029224 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #19