Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3053 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5006. Min Range: -6.5006
Max Act: 6.5006. Min Act: -0.1700
Data Index: 6066988 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5006. Min Range: -6.5006
Max Act: 6.2193. Min Act: -0.1700
Data Index: 5806049 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5006. Min Range: -6.5006
Max Act: 6.1881. Min Act: -0.1700
Data Index: 5806048 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5006. Min Range: -6.5006
Max Act: 6.0318. Min Act: -0.1700
Data Index: 95783 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5006. Min Range: -6.5006
Max Act: 6.0006. Min Act: -0.1700
Data Index: 5806047 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5006. Min Range: -6.5006
Max Act: 5.9693. Min Act: -0.1700
Data Index: 8166707 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5006. Min Range: -6.5006
Max Act: 5.9693. Min Act: -0.1700
Data Index: 7000344 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5006. Min Range: -6.5006
Max Act: 5.9068. Min Act: -0.1700
Data Index: 5893860 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5006. Min Range: -6.5006
Max Act: 5.9068. Min Act: -0.1700
Data Index: 5552476 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5006. Min Range: -6.5006
Max Act: 5.8443. Min Act: -0.1700
Data Index: 970886 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5006. Min Range: -6.5006
Max Act: 5.8443. Min Act: -0.1700
Data Index: 4473965 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5006. Min Range: -6.5006
Max Act: 5.8131. Min Act: -0.1700
Data Index: 5443296 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5006. Min Range: -6.5006
Max Act: 5.7818. Min Act: -0.1700
Data Index: 8818716 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5006. Min Range: -6.5006
Max Act: 5.7818. Min Act: -0.1700
Data Index: 7959185 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5006. Min Range: -6.5006
Max Act: 5.7506. Min Act: -0.1700
Data Index: 341077 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5006. Min Range: -6.5006
Max Act: 5.7506. Min Act: -0.1700
Data Index: 8307977 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5006. Min Range: -6.5006
Max Act: 5.7506. Min Act: -0.1700
Data Index: 855856 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5006. Min Range: -6.5006
Max Act: 5.7193. Min Act: -0.1700
Data Index: 6066987 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5006. Min Range: -6.5006
Max Act: 5.7193. Min Act: -0.1700
Data Index: 4438099 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5006. Min Range: -6.5006
Max Act: 5.7506. Min Act: -0.1700
Data Index: 5200200 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #19