Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3631 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2812. Min Range: -6.2812
Max Act: 6.2812. Min Act: -0.1700
Data Index: 224524 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2812. Min Range: -6.2812
Max Act: 6.2500. Min Act: -0.1700
Data Index: 224521 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2812. Min Range: -6.2812
Max Act: 6.1562. Min Act: -0.1700
Data Index: 663079 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2812. Min Range: -6.2812
Max Act: 6.1250. Min Act: -0.1700
Data Index: 6156027 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2812. Min Range: -6.2812
Max Act: 5.9062. Min Act: -0.1700
Data Index: 3341721 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2812. Min Range: -6.2812
Max Act: 5.9687. Min Act: -0.1700
Data Index: 5086325 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2812. Min Range: -6.2812
Max Act: 5.9062. Min Act: -0.1700
Data Index: 3006664 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2812. Min Range: -6.2812
Max Act: 5.9062. Min Act: -0.1700
Data Index: 6588481 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2812. Min Range: -6.2812
Max Act: 5.8437. Min Act: -0.1700
Data Index: 2136804 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2812. Min Range: -6.2812
Max Act: 5.7187. Min Act: -0.1700
Data Index: 7660170 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2812. Min Range: -6.2812
Max Act: 5.6250. Min Act: -0.1700
Data Index: 7940407 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2812. Min Range: -6.2812
Max Act: 5.5937. Min Act: -0.1700
Data Index: 4016869 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2812. Min Range: -6.2812
Max Act: 5.5625. Min Act: -0.1700
Data Index: 181828 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2812. Min Range: -6.2812
Max Act: 5.5312. Min Act: -0.1700
Data Index: 5377114 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2812. Min Range: -6.2812
Max Act: 5.4687. Min Act: -0.1700
Data Index: 7304813 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2812. Min Range: -6.2812
Max Act: 5.5312. Min Act: -0.1700
Data Index: 997124 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2812. Min Range: -6.2812
Max Act: 5.4687. Min Act: -0.1700
Data Index: 7736244 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2812. Min Range: -6.2812
Max Act: 5.4687. Min Act: -0.1700
Data Index: 8381860 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2812. Min Range: -6.2812
Max Act: 5.4687. Min Act: -0.1700
Data Index: 2205303 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2812. Min Range: -6.2812
Max Act: 5.4062. Min Act: -0.1700
Data Index: 8381865 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #19