Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 44 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2812. Min Range: -8.2812
Max Act: 8.2812. Min Act: -0.1700
Data Index: 3912641 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2812. Min Range: -8.2812
Max Act: 8.0000. Min Act: -0.1700
Data Index: 4859719 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2812. Min Range: -8.2812
Max Act: 7.9687. Min Act: -0.1700
Data Index: 3920348 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2812. Min Range: -8.2812
Max Act: 7.9062. Min Act: -0.1700
Data Index: 2745237 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2812. Min Range: -8.2812
Max Act: 7.8750. Min Act: -0.1700
Data Index: 1943921 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2812. Min Range: -8.2812
Max Act: 7.8437. Min Act: -0.1700
Data Index: 6932859 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2812. Min Range: -8.2812
Max Act: 7.8437. Min Act: -0.1700
Data Index: 6392820 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2812. Min Range: -8.2812
Max Act: 7.8437. Min Act: -0.1700
Data Index: 6147949 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2812. Min Range: -8.2812
Max Act: 7.7812. Min Act: -0.1700
Data Index: 1166792 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2812. Min Range: -8.2812
Max Act: 7.7500. Min Act: -0.1700
Data Index: 6606321 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2812. Min Range: -8.2812
Max Act: 7.7500. Min Act: -0.1700
Data Index: 4234511 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2812. Min Range: -8.2812
Max Act: 7.7500. Min Act: -0.1700
Data Index: 8610668 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2812. Min Range: -8.2812
Max Act: 7.6875. Min Act: -0.1700
Data Index: 4722994 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2812. Min Range: -8.2812
Max Act: 7.6875. Min Act: -0.1700
Data Index: 5490178 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2812. Min Range: -8.2812
Max Act: 7.6875. Min Act: -0.1700
Data Index: 1777569 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2812. Min Range: -8.2812
Max Act: 7.6875. Min Act: -0.1700
Data Index: 3359151 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2812. Min Range: -8.2812
Max Act: 7.6562. Min Act: -0.1700
Data Index: 5995697 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2812. Min Range: -8.2812
Max Act: 7.5937. Min Act: -0.1700
Data Index: 6692184 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2812. Min Range: -8.2812
Max Act: 7.5625. Min Act: -0.1700
Data Index: 6822536 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2812. Min Range: -8.2812
Max Act: 7.5625. Min Act: -0.1700
Data Index: 5488927 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #19