Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3463 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5654. Min Range: -6.5654
Max Act: 6.5654. Min Act: -0.1700
Data Index: 6836779 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5654. Min Range: -6.5654
Max Act: 6.1279. Min Act: -0.1700
Data Index: 7959657 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5654. Min Range: -6.5654
Max Act: 6.0341. Min Act: -0.1700
Data Index: 514964 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5654. Min Range: -6.5654
Max Act: 6.0341. Min Act: -0.1700
Data Index: 6122253 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5654. Min Range: -6.5654
Max Act: 6.0029. Min Act: -0.1700
Data Index: 6053730 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5654. Min Range: -6.5654
Max Act: 5.9404. Min Act: -0.1700
Data Index: 504233 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5654. Min Range: -6.5654
Max Act: 5.9091. Min Act: -0.1700
Data Index: 8186840 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5654. Min Range: -6.5654
Max Act: 5.9091. Min Act: -0.1700
Data Index: 5271873 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5654. Min Range: -6.5654
Max Act: 5.9091. Min Act: -0.1700
Data Index: 5970601 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5654. Min Range: -6.5654
Max Act: 5.8779. Min Act: -0.1700
Data Index: 2304451 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5654. Min Range: -6.5654
Max Act: 5.8779. Min Act: -0.1700
Data Index: 4559654 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5654. Min Range: -6.5654
Max Act: 5.8466. Min Act: -0.1700
Data Index: 1033012 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5654. Min Range: -6.5654
Max Act: 5.8154. Min Act: -0.1700
Data Index: 4148525 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5654. Min Range: -6.5654
Max Act: 5.8154. Min Act: -0.1700
Data Index: 3591143 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5654. Min Range: -6.5654
Max Act: 5.8154. Min Act: -0.1700
Data Index: 7069029 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5654. Min Range: -6.5654
Max Act: 5.8154. Min Act: -0.1700
Data Index: 5406601 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5654. Min Range: -6.5654
Max Act: 5.8154. Min Act: -0.1700
Data Index: 1594137 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5654. Min Range: -6.5654
Max Act: 5.7529. Min Act: -0.1700
Data Index: 4724492 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5654. Min Range: -6.5654
Max Act: 5.7841. Min Act: -0.1700
Data Index: 6676895 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5654. Min Range: -6.5654
Max Act: 5.7529. Min Act: -0.1700
Data Index: 8525757 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #19