Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6119 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0032. Min Range: -8.0032
Max Act: 8.0032. Min Act: -0.1700
Data Index: 1764242 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0032. Min Range: -8.0032
Max Act: 7.9407. Min Act: -0.1700
Data Index: 3430631 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0032. Min Range: -8.0032
Max Act: 7.9407. Min Act: -0.1700
Data Index: 883602 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0032. Min Range: -8.0032
Max Act: 7.9407. Min Act: -0.1700
Data Index: 8749134 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0032. Min Range: -8.0032
Max Act: 7.8782. Min Act: -0.1700
Data Index: 8008060 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0032. Min Range: -8.0032
Max Act: 7.8782. Min Act: -0.1700
Data Index: 2799259 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0032. Min Range: -8.0032
Max Act: 7.8782. Min Act: -0.1700
Data Index: 2139347 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0032. Min Range: -8.0032
Max Act: 7.8782. Min Act: -0.1700
Data Index: 769670 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0032. Min Range: -8.0032
Max Act: 7.8782. Min Act: -0.1700
Data Index: 3427048 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0032. Min Range: -8.0032
Max Act: 7.8782. Min Act: -0.1700
Data Index: 7696205 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0032. Min Range: -8.0032
Max Act: 7.8782. Min Act: -0.1700
Data Index: 6148532 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0032. Min Range: -8.0032
Max Act: 7.8782. Min Act: -0.1700
Data Index: 4939216 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0032. Min Range: -8.0032
Max Act: 7.8782. Min Act: -0.1700
Data Index: 4115852 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0032. Min Range: -8.0032
Max Act: 7.8782. Min Act: -0.1700
Data Index: 3548916 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0032. Min Range: -8.0032
Max Act: 7.8782. Min Act: -0.1700
Data Index: 1660382 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0032. Min Range: -8.0032
Max Act: 7.8782. Min Act: -0.1700
Data Index: 613738 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0032. Min Range: -8.0032
Max Act: 7.7532. Min Act: -0.1700
Data Index: 2452507 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0032. Min Range: -8.0032
Max Act: 7.8157. Min Act: -0.1700
Data Index: 2483929 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0032. Min Range: -8.0032
Max Act: 7.8157. Min Act: -0.1700
Data Index: 2815993 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0032. Min Range: -8.0032
Max Act: 7.8157. Min Act: -0.1700
Data Index: 2954872 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #19