Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 413 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.8807. Min Range: -5.8807
Max Act: 5.8807. Min Act: -0.1700
Data Index: 4993532 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8807. Min Range: -5.8807
Max Act: 5.8495. Min Act: -0.1700
Data Index: 1414774 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8807. Min Range: -5.8807
Max Act: 5.8807. Min Act: -0.1700
Data Index: 6414960 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8807. Min Range: -5.8807
Max Act: 5.8495. Min Act: -0.1700
Data Index: 7256563 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8807. Min Range: -5.8807
Max Act: 5.8495. Min Act: -0.1700
Data Index: 1106203 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8807. Min Range: -5.8807
Max Act: 5.8182. Min Act: -0.1700
Data Index: 5684623 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8807. Min Range: -5.8807
Max Act: 5.8182. Min Act: -0.1700
Data Index: 6508849 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8807. Min Range: -5.8807
Max Act: 5.7870. Min Act: -0.1700
Data Index: 694060 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8807. Min Range: -5.8807
Max Act: 5.7870. Min Act: -0.1700
Data Index: 8278162 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8807. Min Range: -5.8807
Max Act: 5.7870. Min Act: -0.1700
Data Index: 8488067 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8807. Min Range: -5.8807
Max Act: 5.7870. Min Act: -0.1700
Data Index: 3419532 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8807. Min Range: -5.8807
Max Act: 5.7870. Min Act: -0.1700
Data Index: 4912131 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8807. Min Range: -5.8807
Max Act: 5.7870. Min Act: -0.1700
Data Index: 3588917 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8807. Min Range: -5.8807
Max Act: 5.7557. Min Act: -0.1700
Data Index: 4989563 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8807. Min Range: -5.8807
Max Act: 5.7245. Min Act: -0.1700
Data Index: 3760971 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8807. Min Range: -5.8807
Max Act: 5.7557. Min Act: -0.1700
Data Index: 8027972 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8807. Min Range: -5.8807
Max Act: 5.7870. Min Act: -0.1700
Data Index: 4541255 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8807. Min Range: -5.8807
Max Act: 5.7557. Min Act: -0.1700
Data Index: 147302 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8807. Min Range: -5.8807
Max Act: 5.7245. Min Act: -0.1700
Data Index: 4707847 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8807. Min Range: -5.8807
Max Act: 5.7245. Min Act: -0.1700
Data Index: 6529574 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #19