Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4278 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9747. Min Range: -8.9747
Max Act: 8.9747. Min Act: -0.1700
Data Index: 4766581 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9747. Min Range: -8.9747
Max Act: 8.8497. Min Act: -0.1700
Data Index: 2623923 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9747. Min Range: -8.9747
Max Act: 8.5372. Min Act: -0.1700
Data Index: 3010408 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9747. Min Range: -8.9747
Max Act: 8.4122. Min Act: -0.1700
Data Index: 6877744 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9747. Min Range: -8.9747
Max Act: 8.4122. Min Act: -0.1700
Data Index: 7652290 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9747. Min Range: -8.9747
Max Act: 8.4122. Min Act: -0.1700
Data Index: 8502028 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9747. Min Range: -8.9747
Max Act: 8.2247. Min Act: -0.1700
Data Index: 5556968 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9747. Min Range: -8.9747
Max Act: 8.2247. Min Act: -0.1700
Data Index: 3895478 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9747. Min Range: -8.9747
Max Act: 8.1622. Min Act: -0.1700
Data Index: 1647506 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9747. Min Range: -8.9747
Max Act: 8.1622. Min Act: -0.1700
Data Index: 1282069 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9747. Min Range: -8.9747
Max Act: 8.1622. Min Act: -0.1700
Data Index: 5766858 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9747. Min Range: -8.9747
Max Act: 8.1622. Min Act: -0.1700
Data Index: 1311633 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9747. Min Range: -8.9747
Max Act: 8.2247. Min Act: -0.1700
Data Index: 8392103 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9747. Min Range: -8.9747
Max Act: 8.0997. Min Act: -0.1700
Data Index: 747785 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9747. Min Range: -8.9747
Max Act: 8.0997. Min Act: -0.1700
Data Index: 4246958 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9747. Min Range: -8.9747
Max Act: 8.0997. Min Act: -0.1700
Data Index: 6141642 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9747. Min Range: -8.9747
Max Act: 8.0997. Min Act: -0.1700
Data Index: 7250905 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9747. Min Range: -8.9747
Max Act: 8.0997. Min Act: -0.1700
Data Index: 5179914 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9747. Min Range: -8.9747
Max Act: 8.0997. Min Act: -0.1700
Data Index: 3986755 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9747. Min Range: -8.9747
Max Act: 8.0997. Min Act: -0.1700
Data Index: 566081 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #19