Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4987 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 13.0262. Min Range: -13.0262
Max Act: 13.0262. Min Act: -0.1700
Data Index: 5752484 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 13.0262. Min Range: -13.0262
Max Act: 12.5887. Min Act: -0.1700
Data Index: 3826907 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 13.0262. Min Range: -13.0262
Max Act: 12.4637. Min Act: -0.1700
Data Index: 1722477 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 13.0262. Min Range: -13.0262
Max Act: 12.4637. Min Act: -0.1700
Data Index: 5949590 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 13.0262. Min Range: -13.0262
Max Act: 12.4012. Min Act: -0.1700
Data Index: 2550517 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 13.0262. Min Range: -13.0262
Max Act: 12.3387. Min Act: -0.1700
Data Index: 1967282 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 13.0262. Min Range: -13.0262
Max Act: 12.3387. Min Act: -0.1700
Data Index: 4725887 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 13.0262. Min Range: -13.0262
Max Act: 12.2762. Min Act: -0.1700
Data Index: 4890501 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 13.0262. Min Range: -13.0262
Max Act: 12.2137. Min Act: -0.1700
Data Index: 4170335 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 13.0262. Min Range: -13.0262
Max Act: 12.2137. Min Act: -0.1700
Data Index: 1007731 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 13.0262. Min Range: -13.0262
Max Act: 12.2137. Min Act: -0.1700
Data Index: 331425 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 13.0262. Min Range: -13.0262
Max Act: 12.1512. Min Act: -0.1700
Data Index: 5789205 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 13.0262. Min Range: -13.0262
Max Act: 12.2137. Min Act: -0.1700
Data Index: 1099156 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 13.0262. Min Range: -13.0262
Max Act: 12.0887. Min Act: -0.1700
Data Index: 251866 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 13.0262. Min Range: -13.0262
Max Act: 12.0887. Min Act: -0.1700
Data Index: 207498 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 13.0262. Min Range: -13.0262
Max Act: 12.0887. Min Act: -0.1700
Data Index: 1004359 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 13.0262. Min Range: -13.0262
Max Act: 12.0262. Min Act: -0.1700
Data Index: 1614459 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 13.0262. Min Range: -13.0262
Max Act: 11.9637. Min Act: -0.1700
Data Index: 2210558 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 13.0262. Min Range: -13.0262
Max Act: 12.0262. Min Act: -0.1700
Data Index: 5125186 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 13.0262. Min Range: -13.0262
Max Act: 12.0262. Min Act: -0.1700
Data Index: 7695142 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #19