Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1778 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0718. Min Range: -6.0718
Max Act: 6.0718. Min Act: -0.1700
Data Index: 8126919 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0718. Min Range: -6.0718
Max Act: 5.9155. Min Act: -0.1700
Data Index: 4578865 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0718. Min Range: -6.0718
Max Act: 5.9155. Min Act: -0.1700
Data Index: 595100 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0718. Min Range: -6.0718
Max Act: 5.8843. Min Act: -0.1700
Data Index: 8060034 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0718. Min Range: -6.0718
Max Act: 5.7905. Min Act: -0.1700
Data Index: 4812769 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0718. Min Range: -6.0718
Max Act: 5.7905. Min Act: -0.1700
Data Index: 7601012 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0718. Min Range: -6.0718
Max Act: 5.6968. Min Act: -0.1700
Data Index: 4262491 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0718. Min Range: -6.0718
Max Act: 5.6030. Min Act: -0.1700
Data Index: 5560535 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0718. Min Range: -6.0718
Max Act: 5.6343. Min Act: -0.1700
Data Index: 350312 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0718. Min Range: -6.0718
Max Act: 5.6030. Min Act: -0.1700
Data Index: 2049773 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0718. Min Range: -6.0718
Max Act: 5.5718. Min Act: -0.1700
Data Index: 6279073 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0718. Min Range: -6.0718
Max Act: 5.5718. Min Act: -0.1700
Data Index: 4591658 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0718. Min Range: -6.0718
Max Act: 5.5093. Min Act: -0.1700
Data Index: 5007707 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0718. Min Range: -6.0718
Max Act: 5.5405. Min Act: -0.1700
Data Index: 455092 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0718. Min Range: -6.0718
Max Act: 5.4780. Min Act: -0.1700
Data Index: 2522632 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0718. Min Range: -6.0718
Max Act: 5.4780. Min Act: -0.1700
Data Index: 7423358 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0718. Min Range: -6.0718
Max Act: 5.4468. Min Act: -0.1700
Data Index: 1416345 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0718. Min Range: -6.0718
Max Act: 5.4155. Min Act: -0.1700
Data Index: 3516634 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0718. Min Range: -6.0718
Max Act: 5.4468. Min Act: -0.1700
Data Index: 7960139 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0718. Min Range: -6.0718
Max Act: 5.4780. Min Act: -0.1700
Data Index: 648018 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #19