Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6027 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6099. Min Range: -6.6099
Max Act: 6.6099. Min Act: -0.1700
Data Index: 2714377 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6099. Min Range: -6.6099
Max Act: 6.2974. Min Act: -0.1700
Data Index: 1024441 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6099. Min Range: -6.6099
Max Act: 6.2662. Min Act: -0.1700
Data Index: 1375613 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6099. Min Range: -6.6099
Max Act: 6.2974. Min Act: -0.1700
Data Index: 6367732 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6099. Min Range: -6.6099
Max Act: 6.2037. Min Act: -0.1700
Data Index: 446619 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6099. Min Range: -6.6099
Max Act: 6.2037. Min Act: -0.1700
Data Index: 6057315 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6099. Min Range: -6.6099
Max Act: 6.1412. Min Act: -0.1700
Data Index: 5177537 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6099. Min Range: -6.6099
Max Act: 6.1724. Min Act: -0.1700
Data Index: 6975663 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6099. Min Range: -6.6099
Max Act: 6.1412. Min Act: -0.1700
Data Index: 686080 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6099. Min Range: -6.6099
Max Act: 6.0787. Min Act: -0.1700
Data Index: 4057176 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6099. Min Range: -6.6099
Max Act: 6.1099. Min Act: -0.1700
Data Index: 3166528 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6099. Min Range: -6.6099
Max Act: 6.0787. Min Act: -0.1700
Data Index: 6585614 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6099. Min Range: -6.6099
Max Act: 6.0787. Min Act: -0.1700
Data Index: 4453539 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6099. Min Range: -6.6099
Max Act: 6.0787. Min Act: -0.1700
Data Index: 358808 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6099. Min Range: -6.6099
Max Act: 6.0787. Min Act: -0.1700
Data Index: 7287371 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6099. Min Range: -6.6099
Max Act: 6.0787. Min Act: -0.1700
Data Index: 5324230 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6099. Min Range: -6.6099
Max Act: 6.0474. Min Act: -0.1700
Data Index: 6304869 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6099. Min Range: -6.6099
Max Act: 6.0474. Min Act: -0.1700
Data Index: 7131469 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6099. Min Range: -6.6099
Max Act: 6.0474. Min Act: -0.1700
Data Index: 5885087 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6099. Min Range: -6.6099
Max Act: 6.0474. Min Act: -0.1700
Data Index: 2468810 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #19