Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2607 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8750. Min Range: -4.8750
Max Act: 4.8750. Min Act: -0.1700
Data Index: 316493 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8750. Min Range: -4.8750
Max Act: 4.5937. Min Act: -0.1700
Data Index: 6329285 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8750. Min Range: -4.8750
Max Act: 4.5937. Min Act: -0.1700
Data Index: 2996406 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8750. Min Range: -4.8750
Max Act: 4.5937. Min Act: -0.1700
Data Index: 4763462 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8750. Min Range: -4.8750
Max Act: 4.5625. Min Act: -0.1700
Data Index: 7160818 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8750. Min Range: -4.8750
Max Act: 4.5000. Min Act: -0.1700
Data Index: 7642844 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8750. Min Range: -4.8750
Max Act: 4.5000. Min Act: -0.1700
Data Index: 8501452 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8750. Min Range: -4.8750
Max Act: 4.4375. Min Act: -0.1700
Data Index: 8195250 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8750. Min Range: -4.8750
Max Act: 4.4687. Min Act: -0.1700
Data Index: 2189066 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8750. Min Range: -4.8750
Max Act: 4.4375. Min Act: -0.1700
Data Index: 1067602 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8750. Min Range: -4.8750
Max Act: 4.4062. Min Act: -0.1700
Data Index: 6372258 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8750. Min Range: -4.8750
Max Act: 4.4062. Min Act: -0.1700
Data Index: 8796391 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8750. Min Range: -4.8750
Max Act: 4.4062. Min Act: -0.1700
Data Index: 4933844 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8750. Min Range: -4.8750
Max Act: 4.4062. Min Act: -0.1700
Data Index: 7642847 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8750. Min Range: -4.8750
Max Act: 4.4062. Min Act: -0.1700
Data Index: 8431263 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8750. Min Range: -4.8750
Max Act: 4.4062. Min Act: -0.1700
Data Index: 757764 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8750. Min Range: -4.8750
Max Act: 4.3750. Min Act: -0.1700
Data Index: 595943 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8750. Min Range: -4.8750
Max Act: 4.3750. Min Act: -0.1700
Data Index: 6058224 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8750. Min Range: -4.8750
Max Act: 4.3750. Min Act: -0.1700
Data Index: 7916521 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8750. Min Range: -4.8750
Max Act: 4.3750. Min Act: -0.1700
Data Index: 7934076 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #19