Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6127 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6639. Min Range: -5.6639
Max Act: 5.6639. Min Act: -0.1700
Data Index: 4337378 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6639. Min Range: -5.6639
Max Act: 5.4139. Min Act: -0.1700
Data Index: 3932145 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6639. Min Range: -5.6639
Max Act: 5.3514. Min Act: -0.1700
Data Index: 419958 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6639. Min Range: -5.6639
Max Act: 5.2889. Min Act: -0.1700
Data Index: 1308675 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6639. Min Range: -5.6639
Max Act: 5.2264. Min Act: -0.1700
Data Index: 8079829 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6639. Min Range: -5.6639
Max Act: 5.2264. Min Act: -0.1700
Data Index: 7531481 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6639. Min Range: -5.6639
Max Act: 5.2264. Min Act: -0.1700
Data Index: 7863637 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6639. Min Range: -5.6639
Max Act: 5.1951. Min Act: -0.1700
Data Index: 4694423 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6639. Min Range: -5.6639
Max Act: 5.1639. Min Act: -0.1700
Data Index: 7692325 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6639. Min Range: -5.6639
Max Act: 5.1326. Min Act: -0.1700
Data Index: 998082 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6639. Min Range: -5.6639
Max Act: 5.1326. Min Act: -0.1700
Data Index: 3904210 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6639. Min Range: -5.6639
Max Act: 5.0389. Min Act: -0.1700
Data Index: 1672345 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6639. Min Range: -5.6639
Max Act: 5.0701. Min Act: -0.1700
Data Index: 4756259 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6639. Min Range: -5.6639
Max Act: 5.0701. Min Act: -0.1700
Data Index: 1027295 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6639. Min Range: -5.6639
Max Act: 5.0389. Min Act: -0.1700
Data Index: 4632412 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6639. Min Range: -5.6639
Max Act: 5.0389. Min Act: -0.1700
Data Index: 7289532 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6639. Min Range: -5.6639
Max Act: 5.0389. Min Act: -0.1700
Data Index: 4831814 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6639. Min Range: -5.6639
Max Act: 5.0389. Min Act: -0.1700
Data Index: 6213755 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6639. Min Range: -5.6639
Max Act: 5.0076. Min Act: -0.1700
Data Index: 2761616 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6639. Min Range: -5.6639
Max Act: 5.0076. Min Act: -0.1700
Data Index: 3077716 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #19