Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5769 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9807. Min Range: -3.9807
Max Act: 3.9807. Min Act: -0.1700
Data Index: 1637776 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9807. Min Range: -3.9807
Max Act: 3.9495. Min Act: -0.1700
Data Index: 5055716 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9807. Min Range: -3.9807
Max Act: 3.9182. Min Act: -0.1700
Data Index: 4331652 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9807. Min Range: -3.9807
Max Act: 3.9182. Min Act: -0.1700
Data Index: 6904418 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9807. Min Range: -3.9807
Max Act: 3.8557. Min Act: -0.1700
Data Index: 2098076 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9807. Min Range: -3.9807
Max Act: 3.7775. Min Act: -0.1700
Data Index: 8683661 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9807. Min Range: -3.9807
Max Act: 3.6993. Min Act: -0.1700
Data Index: 972546 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9807. Min Range: -3.9807
Max Act: 3.6837. Min Act: -0.1700
Data Index: 7928925 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9807. Min Range: -3.9807
Max Act: 3.6524. Min Act: -0.1700
Data Index: 2183732 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9807. Min Range: -3.9807
Max Act: 3.6524. Min Act: -0.1700
Data Index: 8120040 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9807. Min Range: -3.9807
Max Act: 3.6524. Min Act: -0.1700
Data Index: 375240 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9807. Min Range: -3.9807
Max Act: 3.6367. Min Act: -0.1700
Data Index: 123632 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9807. Min Range: -3.9807
Max Act: 3.6367. Min Act: -0.1700
Data Index: 2091726 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9807. Min Range: -3.9807
Max Act: 3.6367. Min Act: -0.1700
Data Index: 1604042 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9807. Min Range: -3.9807
Max Act: 3.6211. Min Act: -0.1700
Data Index: 7166592 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9807. Min Range: -3.9807
Max Act: 3.6054. Min Act: -0.1700
Data Index: 486819 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9807. Min Range: -3.9807
Max Act: 3.6211. Min Act: -0.1700
Data Index: 3345938 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9807. Min Range: -3.9807
Max Act: 3.6054. Min Act: -0.1700
Data Index: 2922002 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9807. Min Range: -3.9807
Max Act: 3.6211. Min Act: -0.1700
Data Index: 5339258 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9807. Min Range: -3.9807
Max Act: 3.6054. Min Act: -0.1700
Data Index: 1108157 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #19