Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5139 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9376. Min Range: -5.9376
Max Act: 5.9376. Min Act: -0.1700
Data Index: 5915598 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9376. Min Range: -5.9376
Max Act: 5.8438. Min Act: -0.1700
Data Index: 1050021 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9376. Min Range: -5.9376
Max Act: 5.8126. Min Act: -0.1700
Data Index: 7735206 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9376. Min Range: -5.9376
Max Act: 5.7813. Min Act: -0.1700
Data Index: 7198086 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9376. Min Range: -5.9376
Max Act: 5.6876. Min Act: -0.1700
Data Index: 3080344 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9376. Min Range: -5.9376
Max Act: 5.5938. Min Act: -0.1700
Data Index: 5680356 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9376. Min Range: -5.9376
Max Act: 5.5626. Min Act: -0.1700
Data Index: 5578220 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9376. Min Range: -5.9376
Max Act: 5.5313. Min Act: -0.1700
Data Index: 5578221 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9376. Min Range: -5.9376
Max Act: 5.5313. Min Act: -0.1700
Data Index: 5296276 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9376. Min Range: -5.9376
Max Act: 5.5001. Min Act: -0.1700
Data Index: 6616042 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9376. Min Range: -5.9376
Max Act: 5.5001. Min Act: -0.1700
Data Index: 7735207 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9376. Min Range: -5.9376
Max Act: 5.5001. Min Act: -0.1700
Data Index: 4728311 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9376. Min Range: -5.9376
Max Act: 5.4688. Min Act: -0.1700
Data Index: 4193969 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9376. Min Range: -5.9376
Max Act: 5.4376. Min Act: -0.1700
Data Index: 1050022 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9376. Min Range: -5.9376
Max Act: 5.4376. Min Act: -0.1700
Data Index: 4132332 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9376. Min Range: -5.9376
Max Act: 5.4376. Min Act: -0.1700
Data Index: 1960904 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9376. Min Range: -5.9376
Max Act: 5.4063. Min Act: -0.1700
Data Index: 4153618 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9376. Min Range: -5.9376
Max Act: 5.4376. Min Act: -0.1700
Data Index: 3497778 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9376. Min Range: -5.9376
Max Act: 5.4063. Min Act: -0.1700
Data Index: 1152 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9376. Min Range: -5.9376
Max Act: 5.3438. Min Act: -0.1700
Data Index: 5915599 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #19