Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3741 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6164. Min Range: -6.6164
Max Act: 6.6164. Min Act: -0.1700
Data Index: 5980737 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6164. Min Range: -6.6164
Max Act: 6.5851. Min Act: -0.1700
Data Index: 7774637 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6164. Min Range: -6.6164
Max Act: 6.5851. Min Act: -0.1700
Data Index: 6945978 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6164. Min Range: -6.6164
Max Act: 6.5226. Min Act: -0.1700
Data Index: 2458035 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6164. Min Range: -6.6164
Max Act: 6.4914. Min Act: -0.1700
Data Index: 4240026 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6164. Min Range: -6.6164
Max Act: 6.4601. Min Act: -0.1700
Data Index: 521320 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6164. Min Range: -6.6164
Max Act: 6.4289. Min Act: -0.1700
Data Index: 7794338 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6164. Min Range: -6.6164
Max Act: 6.4289. Min Act: -0.1700
Data Index: 3843867 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6164. Min Range: -6.6164
Max Act: 6.4289. Min Act: -0.1700
Data Index: 7088524 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6164. Min Range: -6.6164
Max Act: 6.3976. Min Act: -0.1700
Data Index: 8759799 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6164. Min Range: -6.6164
Max Act: 6.3976. Min Act: -0.1700
Data Index: 8195005 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6164. Min Range: -6.6164
Max Act: 6.3664. Min Act: -0.1700
Data Index: 7400482 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6164. Min Range: -6.6164
Max Act: 6.3664. Min Act: -0.1700
Data Index: 6594107 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6164. Min Range: -6.6164
Max Act: 6.3664. Min Act: -0.1700
Data Index: 6559298 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6164. Min Range: -6.6164
Max Act: 6.3351. Min Act: -0.1700
Data Index: 976242 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6164. Min Range: -6.6164
Max Act: 6.3351. Min Act: -0.1700
Data Index: 3176573 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6164. Min Range: -6.6164
Max Act: 6.3039. Min Act: -0.1700
Data Index: 5318290 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6164. Min Range: -6.6164
Max Act: 6.3039. Min Act: -0.1700
Data Index: 7263525 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6164. Min Range: -6.6164
Max Act: 6.3039. Min Act: -0.1700
Data Index: 6970491 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6164. Min Range: -6.6164
Max Act: 6.3039. Min Act: -0.1700
Data Index: 6268990 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #19