Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5155 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 12.3704. Min Range: -12.3704
Max Act: 12.3704. Min Act: -0.1700
Data Index: 4831647 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.3704. Min Range: -12.3704
Max Act: 12.3079. Min Act: -0.1700
Data Index: 5195518 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.3704. Min Range: -12.3704
Max Act: 12.2454. Min Act: -0.1700
Data Index: 467751 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.3704. Min Range: -12.3704
Max Act: 12.1204. Min Act: -0.1700
Data Index: 1911363 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.3704. Min Range: -12.3704
Max Act: 12.1204. Min Act: -0.1700
Data Index: 4211872 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.3704. Min Range: -12.3704
Max Act: 11.9954. Min Act: -0.1700
Data Index: 2166880 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.3704. Min Range: -12.3704
Max Act: 11.9954. Min Act: -0.1700
Data Index: 5986431 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.3704. Min Range: -12.3704
Max Act: 11.9329. Min Act: -0.1700
Data Index: 2930734 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.3704. Min Range: -12.3704
Max Act: 11.9329. Min Act: -0.1700
Data Index: 1246015 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.3704. Min Range: -12.3704
Max Act: 11.9329. Min Act: -0.1700
Data Index: 8576913 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.3704. Min Range: -12.3704
Max Act: 11.8704. Min Act: -0.1700
Data Index: 1810975 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.3704. Min Range: -12.3704
Max Act: 11.8704. Min Act: -0.1700
Data Index: 3344243 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.3704. Min Range: -12.3704
Max Act: 11.8079. Min Act: -0.1700
Data Index: 6335847 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.3704. Min Range: -12.3704
Max Act: 11.8079. Min Act: -0.1700
Data Index: 3484616 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.3704. Min Range: -12.3704
Max Act: 11.8079. Min Act: -0.1700
Data Index: 3297986 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.3704. Min Range: -12.3704
Max Act: 11.8079. Min Act: -0.1700
Data Index: 4172725 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.3704. Min Range: -12.3704
Max Act: 11.8079. Min Act: -0.1700
Data Index: 4711264 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.3704. Min Range: -12.3704
Max Act: 11.7454. Min Act: -0.1700
Data Index: 5172172 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.3704. Min Range: -12.3704
Max Act: 11.7454. Min Act: -0.1700
Data Index: 3425096 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.3704. Min Range: -12.3704
Max Act: 11.7454. Min Act: -0.1700
Data Index: 6554823 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #19