Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3127 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.7747. Min Range: -10.7747
Max Act: 10.7747. Min Act: -0.1700
Data Index: 8680608 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.7747. Min Range: -10.7747
Max Act: 10.7747. Min Act: -0.1700
Data Index: 2186611 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.7747. Min Range: -10.7747
Max Act: 10.5247. Min Act: -0.1700
Data Index: 3500235 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.7747. Min Range: -10.7747
Max Act: 10.3372. Min Act: -0.1700
Data Index: 1061304 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.7747. Min Range: -10.7747
Max Act: 10.1497. Min Act: -0.1700
Data Index: 526023 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.7747. Min Range: -10.7747
Max Act: 10.1497. Min Act: -0.1700
Data Index: 2991863 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.7747. Min Range: -10.7747
Max Act: 10.0247. Min Act: -0.1700
Data Index: 3795293 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.7747. Min Range: -10.7747
Max Act: 10.0247. Min Act: -0.1700
Data Index: 2507650 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.7747. Min Range: -10.7747
Max Act: 9.9622. Min Act: -0.1700
Data Index: 7576735 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.7747. Min Range: -10.7747
Max Act: 9.9622. Min Act: -0.1700
Data Index: 6125529 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.7747. Min Range: -10.7747
Max Act: 9.8997. Min Act: -0.1700
Data Index: 1561900 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.7747. Min Range: -10.7747
Max Act: 9.8372. Min Act: -0.1700
Data Index: 5574642 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.7747. Min Range: -10.7747
Max Act: 9.8372. Min Act: -0.1700
Data Index: 4069020 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.7747. Min Range: -10.7747
Max Act: 9.7122. Min Act: -0.1700
Data Index: 5904926 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.7747. Min Range: -10.7747
Max Act: 9.7747. Min Act: -0.1700
Data Index: 3386247 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.7747. Min Range: -10.7747
Max Act: 9.7122. Min Act: -0.1700
Data Index: 6085958 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.7747. Min Range: -10.7747
Max Act: 9.7122. Min Act: -0.1700
Data Index: 6017104 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.7747. Min Range: -10.7747
Max Act: 9.7122. Min Act: -0.1700
Data Index: 8672731 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.7747. Min Range: -10.7747
Max Act: 9.7122. Min Act: -0.1700
Data Index: 6566954 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.7747. Min Range: -10.7747
Max Act: 9.7122. Min Act: -0.1700
Data Index: 6397115 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #19