Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5166 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8843. Min Range: -6.8843
Max Act: 6.8843. Min Act: -0.1700
Data Index: 7134797 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8843. Min Range: -6.8843
Max Act: 6.7905. Min Act: -0.1700
Data Index: 1280868 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8843. Min Range: -6.8843
Max Act: 6.7593. Min Act: -0.1700
Data Index: 7529977 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8843. Min Range: -6.8843
Max Act: 6.7593. Min Act: -0.1700
Data Index: 7873106 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8843. Min Range: -6.8843
Max Act: 6.7280. Min Act: -0.1700
Data Index: 572838 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8843. Min Range: -6.8843
Max Act: 6.6655. Min Act: -0.1700
Data Index: 1017537 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8843. Min Range: -6.8843
Max Act: 6.6655. Min Act: -0.1700
Data Index: 6291662 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8843. Min Range: -6.8843
Max Act: 6.6655. Min Act: -0.1700
Data Index: 5667963 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8843. Min Range: -6.8843
Max Act: 6.6030. Min Act: -0.1700
Data Index: 1591676 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8843. Min Range: -6.8843
Max Act: 6.5718. Min Act: -0.1700
Data Index: 7629022 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8843. Min Range: -6.8843
Max Act: 6.5718. Min Act: -0.1700
Data Index: 985592 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8843. Min Range: -6.8843
Max Act: 6.5405. Min Act: -0.1700
Data Index: 6361687 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8843. Min Range: -6.8843
Max Act: 6.4780. Min Act: -0.1700
Data Index: 4360103 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8843. Min Range: -6.8843
Max Act: 6.4780. Min Act: -0.1700
Data Index: 8435110 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8843. Min Range: -6.8843
Max Act: 6.4468. Min Act: -0.1700
Data Index: 1771041 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8843. Min Range: -6.8843
Max Act: 6.4468. Min Act: -0.1700
Data Index: 1265968 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8843. Min Range: -6.8843
Max Act: 6.4468. Min Act: -0.1700
Data Index: 4217194 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8843. Min Range: -6.8843
Max Act: 6.4468. Min Act: -0.1700
Data Index: 3777639 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8843. Min Range: -6.8843
Max Act: 6.3843. Min Act: -0.1700
Data Index: 1606570 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8843. Min Range: -6.8843
Max Act: 6.3530. Min Act: -0.1700
Data Index: 4428824 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #19