Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3361 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9731. Min Range: -5.9731
Max Act: 5.9731. Min Act: -0.1700
Data Index: 5199543 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9731. Min Range: -5.9731
Max Act: 5.9418. Min Act: -0.1700
Data Index: 4916356 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9731. Min Range: -5.9731
Max Act: 5.8168. Min Act: -0.1700
Data Index: 34207 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9731. Min Range: -5.9731
Max Act: 5.7856. Min Act: -0.1700
Data Index: 7237073 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9731. Min Range: -5.9731
Max Act: 5.7856. Min Act: -0.1700
Data Index: 7237080 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9731. Min Range: -5.9731
Max Act: 5.7543. Min Act: -0.1700
Data Index: 1173780 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9731. Min Range: -5.9731
Max Act: 5.7856. Min Act: -0.1700
Data Index: 3824204 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9731. Min Range: -5.9731
Max Act: 5.7543. Min Act: -0.1700
Data Index: 5548973 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9731. Min Range: -5.9731
Max Act: 5.7543. Min Act: -0.1700
Data Index: 6872123 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9731. Min Range: -5.9731
Max Act: 5.6918. Min Act: -0.1700
Data Index: 5857415 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9731. Min Range: -5.9731
Max Act: 5.6918. Min Act: -0.1700
Data Index: 2049363 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9731. Min Range: -5.9731
Max Act: 5.6918. Min Act: -0.1700
Data Index: 3258594 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9731. Min Range: -5.9731
Max Act: 5.7231. Min Act: -0.1700
Data Index: 6214487 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9731. Min Range: -5.9731
Max Act: 5.6918. Min Act: -0.1700
Data Index: 996364 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9731. Min Range: -5.9731
Max Act: 5.6293. Min Act: -0.1700
Data Index: 7144247 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9731. Min Range: -5.9731
Max Act: 5.6606. Min Act: -0.1700
Data Index: 6659365 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9731. Min Range: -5.9731
Max Act: 5.6606. Min Act: -0.1700
Data Index: 4079504 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9731. Min Range: -5.9731
Max Act: 5.6606. Min Act: -0.1700
Data Index: 1504775 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9731. Min Range: -5.9731
Max Act: 5.5981. Min Act: -0.1700
Data Index: 4546315 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9731. Min Range: -5.9731
Max Act: 5.6293. Min Act: -0.1700
Data Index: 2860356 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #19