Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2134 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5439. Min Range: -8.5439
Max Act: 8.5439. Min Act: -0.1700
Data Index: 5609721 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5439. Min Range: -8.5439
Max Act: 8.5439. Min Act: -0.1700
Data Index: 8358300 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5439. Min Range: -8.5439
Max Act: 8.2314. Min Act: -0.1700
Data Index: 5457298 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5439. Min Range: -8.5439
Max Act: 8.1689. Min Act: -0.1700
Data Index: 544958 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5439. Min Range: -8.5439
Max Act: 7.8876. Min Act: -0.1700
Data Index: 4146205 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5439. Min Range: -8.5439
Max Act: 7.8876. Min Act: -0.1700
Data Index: 2153343 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5439. Min Range: -8.5439
Max Act: 7.8564. Min Act: -0.1700
Data Index: 3813029 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5439. Min Range: -8.5439
Max Act: 7.8251. Min Act: -0.1700
Data Index: 1891330 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5439. Min Range: -8.5439
Max Act: 7.8251. Min Act: -0.1700
Data Index: 323039 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5439. Min Range: -8.5439
Max Act: 7.8251. Min Act: -0.1700
Data Index: 6789696 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5439. Min Range: -8.5439
Max Act: 7.6064. Min Act: -0.1700
Data Index: 4814895 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5439. Min Range: -8.5439
Max Act: 7.5439. Min Act: -0.1700
Data Index: 1474559 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5439. Min Range: -8.5439
Max Act: 7.5751. Min Act: -0.1700
Data Index: 1106477 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5439. Min Range: -8.5439
Max Act: 7.5751. Min Act: -0.1700
Data Index: 544945 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5439. Min Range: -8.5439
Max Act: 7.5126. Min Act: -0.1700
Data Index: 7027393 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5439. Min Range: -8.5439
Max Act: 7.5126. Min Act: -0.1700
Data Index: 4183633 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5439. Min Range: -8.5439
Max Act: 7.4814. Min Act: -0.1700
Data Index: 1570416 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5439. Min Range: -8.5439
Max Act: 7.4814. Min Act: -0.1700
Data Index: 1474123 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5439. Min Range: -8.5439
Max Act: 7.4814. Min Act: -0.1700
Data Index: 5809282 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5439. Min Range: -8.5439
Max Act: 7.4814. Min Act: -0.1700
Data Index: 883291 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #19