Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4300 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8501. Min Range: -6.8501
Max Act: 6.8501. Min Act: -0.1700
Data Index: 3059929 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8501. Min Range: -6.8501
Max Act: 6.8189. Min Act: -0.1700
Data Index: 1712331 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8501. Min Range: -6.8501
Max Act: 6.7251. Min Act: -0.1700
Data Index: 5966625 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8501. Min Range: -6.8501
Max Act: 6.6939. Min Act: -0.1700
Data Index: 4493765 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8501. Min Range: -6.8501
Max Act: 6.6626. Min Act: -0.1700
Data Index: 222821 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8501. Min Range: -6.8501
Max Act: 6.6626. Min Act: -0.1700
Data Index: 8413715 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8501. Min Range: -6.8501
Max Act: 6.6314. Min Act: -0.1700
Data Index: 6690453 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8501. Min Range: -6.8501
Max Act: 6.6001. Min Act: -0.1700
Data Index: 5137626 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8501. Min Range: -6.8501
Max Act: 6.6001. Min Act: -0.1700
Data Index: 991910 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8501. Min Range: -6.8501
Max Act: 6.6001. Min Act: -0.1700
Data Index: 2738379 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8501. Min Range: -6.8501
Max Act: 6.5689. Min Act: -0.1700
Data Index: 7907064 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8501. Min Range: -6.8501
Max Act: 6.5064. Min Act: -0.1700
Data Index: 5939333 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8501. Min Range: -6.8501
Max Act: 6.3189. Min Act: -0.1700
Data Index: 1564913 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8501. Min Range: -6.8501
Max Act: 6.2876. Min Act: -0.1700
Data Index: 6366612 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8501. Min Range: -6.8501
Max Act: 6.3189. Min Act: -0.1700
Data Index: 6066249 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8501. Min Range: -6.8501
Max Act: 6.2876. Min Act: -0.1700
Data Index: 7373851 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8501. Min Range: -6.8501
Max Act: 6.2876. Min Act: -0.1700
Data Index: 4451495 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8501. Min Range: -6.8501
Max Act: 6.2876. Min Act: -0.1700
Data Index: 115290 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8501. Min Range: -6.8501
Max Act: 6.2564. Min Act: -0.1700
Data Index: 5707407 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8501. Min Range: -6.8501
Max Act: 6.2564. Min Act: -0.1700
Data Index: 5004536 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #19