Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1231 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2164. Min Range: -5.2164
Max Act: 5.2164. Min Act: -0.1700
Data Index: 4617556 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2164. Min Range: -5.2164
Max Act: 5.1851. Min Act: -0.1700
Data Index: 5007296 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2164. Min Range: -5.2164
Max Act: 5.1226. Min Act: -0.1700
Data Index: 441322 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2164. Min Range: -5.2164
Max Act: 5.1226. Min Act: -0.1700
Data Index: 8148649 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2164. Min Range: -5.2164
Max Act: 5.0914. Min Act: -0.1700
Data Index: 7086205 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2164. Min Range: -5.2164
Max Act: 5.0914. Min Act: -0.1700
Data Index: 4517411 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2164. Min Range: -5.2164
Max Act: 5.1226. Min Act: -0.1700
Data Index: 6699261 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2164. Min Range: -5.2164
Max Act: 5.0914. Min Act: -0.1700
Data Index: 274870 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2164. Min Range: -5.2164
Max Act: 5.0601. Min Act: -0.1700
Data Index: 4728857 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2164. Min Range: -5.2164
Max Act: 5.0601. Min Act: -0.1700
Data Index: 8798888 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2164. Min Range: -5.2164
Max Act: 5.0601. Min Act: -0.1700
Data Index: 5978037 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2164. Min Range: -5.2164
Max Act: 4.9976. Min Act: -0.1700
Data Index: 5105977 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2164. Min Range: -5.2164
Max Act: 4.9976. Min Act: -0.1700
Data Index: 6903666 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2164. Min Range: -5.2164
Max Act: 4.9664. Min Act: -0.1700
Data Index: 8256190 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2164. Min Range: -5.2164
Max Act: 4.9664. Min Act: -0.1700
Data Index: 4654222 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2164. Min Range: -5.2164
Max Act: 4.9039. Min Act: -0.1700
Data Index: 8375131 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2164. Min Range: -5.2164
Max Act: 4.9351. Min Act: -0.1700
Data Index: 6591160 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2164. Min Range: -5.2164
Max Act: 4.9351. Min Act: -0.1700
Data Index: 7863351 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2164. Min Range: -5.2164
Max Act: 4.9351. Min Act: -0.1700
Data Index: 372348 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2164. Min Range: -5.2164
Max Act: 4.9351. Min Act: -0.1700
Data Index: 5782574 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #19