Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1921 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4688. Min Range: -6.4688
Max Act: 6.4688. Min Act: -0.1700
Data Index: 6924127 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4688. Min Range: -6.4688
Max Act: 6.1563. Min Act: -0.1700
Data Index: 775811 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4688. Min Range: -6.4688
Max Act: 6.1563. Min Act: -0.1700
Data Index: 7896981 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4688. Min Range: -6.4688
Max Act: 6.1875. Min Act: -0.1700
Data Index: 131732 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4688. Min Range: -6.4688
Max Act: 6.1250. Min Act: -0.1700
Data Index: 43822 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4688. Min Range: -6.4688
Max Act: 6.0938. Min Act: -0.1700
Data Index: 8032255 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4688. Min Range: -6.4688
Max Act: 6.0625. Min Act: -0.1700
Data Index: 2663552 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4688. Min Range: -6.4688
Max Act: 5.9688. Min Act: -0.1700
Data Index: 8476337 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4688. Min Range: -6.4688
Max Act: 6.0313. Min Act: -0.1700
Data Index: 6907066 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4688. Min Range: -6.4688
Max Act: 6.0000. Min Act: -0.1700
Data Index: 804174 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4688. Min Range: -6.4688
Max Act: 5.9688. Min Act: -0.1700
Data Index: 8502970 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4688. Min Range: -6.4688
Max Act: 5.9375. Min Act: -0.1700
Data Index: 1849229 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4688. Min Range: -6.4688
Max Act: 5.9375. Min Act: -0.1700
Data Index: 2025022 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4688. Min Range: -6.4688
Max Act: 5.9375. Min Act: -0.1700
Data Index: 5865460 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4688. Min Range: -6.4688
Max Act: 5.9375. Min Act: -0.1700
Data Index: 7012077 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4688. Min Range: -6.4688
Max Act: 5.9063. Min Act: -0.1700
Data Index: 7729145 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4688. Min Range: -6.4688
Max Act: 5.9063. Min Act: -0.1700
Data Index: 2653180 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4688. Min Range: -6.4688
Max Act: 5.9063. Min Act: -0.1700
Data Index: 5161703 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4688. Min Range: -6.4688
Max Act: 5.9063. Min Act: -0.1700
Data Index: 1554835 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4688. Min Range: -6.4688
Max Act: 5.9063. Min Act: -0.1700
Data Index: 3187339 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #19