Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5158 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.1288. Min Range: -9.1288
Max Act: 9.1288. Min Act: -0.1700
Data Index: 140694 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1288. Min Range: -9.1288
Max Act: 9.0663. Min Act: -0.1700
Data Index: 3254176 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1288. Min Range: -9.1288
Max Act: 9.0038. Min Act: -0.1700
Data Index: 1364527 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1288. Min Range: -9.1288
Max Act: 9.0663. Min Act: -0.1700
Data Index: 6958324 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1288. Min Range: -9.1288
Max Act: 8.9413. Min Act: -0.1700
Data Index: 4937317 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1288. Min Range: -9.1288
Max Act: 8.7538. Min Act: -0.1700
Data Index: 3048056 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1288. Min Range: -9.1288
Max Act: 8.6913. Min Act: -0.1700
Data Index: 4089146 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1288. Min Range: -9.1288
Max Act: 8.6913. Min Act: -0.1700
Data Index: 7903202 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1288. Min Range: -9.1288
Max Act: 8.6913. Min Act: -0.1700
Data Index: 4100412 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1288. Min Range: -9.1288
Max Act: 8.6288. Min Act: -0.1700
Data Index: 4261039 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1288. Min Range: -9.1288
Max Act: 8.6288. Min Act: -0.1700
Data Index: 4450475 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1288. Min Range: -9.1288
Max Act: 8.6288. Min Act: -0.1700
Data Index: 8442458 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1288. Min Range: -9.1288
Max Act: 8.5663. Min Act: -0.1700
Data Index: 4712282 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1288. Min Range: -9.1288
Max Act: 8.5038. Min Act: -0.1700
Data Index: 5756784 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1288. Min Range: -9.1288
Max Act: 8.5038. Min Act: -0.1700
Data Index: 5452406 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1288. Min Range: -9.1288
Max Act: 8.5038. Min Act: -0.1700
Data Index: 1798106 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1288. Min Range: -9.1288
Max Act: 8.5038. Min Act: -0.1700
Data Index: 5919911 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1288. Min Range: -9.1288
Max Act: 8.5038. Min Act: -0.1700
Data Index: 8679911 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1288. Min Range: -9.1288
Max Act: 8.5038. Min Act: -0.1700
Data Index: 7049130 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1288. Min Range: -9.1288
Max Act: 8.4413. Min Act: -0.1700
Data Index: 2208790 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #19