Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2779 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9133. Min Range: -4.9133
Max Act: 4.9133. Min Act: -0.1700
Data Index: 7160632 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9133. Min Range: -4.9133
Max Act: 4.9133. Min Act: -0.1700
Data Index: 5664807 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9133. Min Range: -4.9133
Max Act: 4.8508. Min Act: -0.1700
Data Index: 4110150 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9133. Min Range: -4.9133
Max Act: 4.8508. Min Act: -0.1700
Data Index: 1782862 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9133. Min Range: -4.9133
Max Act: 4.8195. Min Act: -0.1700
Data Index: 4086215 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9133. Min Range: -4.9133
Max Act: 4.7883. Min Act: -0.1700
Data Index: 1279742 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9133. Min Range: -4.9133
Max Act: 4.7883. Min Act: -0.1700
Data Index: 2118483 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9133. Min Range: -4.9133
Max Act: 4.7570. Min Act: -0.1700
Data Index: 4899100 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9133. Min Range: -4.9133
Max Act: 4.7570. Min Act: -0.1700
Data Index: 8022469 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9133. Min Range: -4.9133
Max Act: 4.7258. Min Act: -0.1700
Data Index: 505252 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9133. Min Range: -4.9133
Max Act: 4.7258. Min Act: -0.1700
Data Index: 6601486 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9133. Min Range: -4.9133
Max Act: 4.6945. Min Act: -0.1700
Data Index: 2730100 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9133. Min Range: -4.9133
Max Act: 4.6945. Min Act: -0.1700
Data Index: 375554 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9133. Min Range: -4.9133
Max Act: 4.6945. Min Act: -0.1700
Data Index: 2453173 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9133. Min Range: -4.9133
Max Act: 4.6945. Min Act: -0.1700
Data Index: 790711 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9133. Min Range: -4.9133
Max Act: 4.6633. Min Act: -0.1700
Data Index: 5680705 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9133. Min Range: -4.9133
Max Act: 4.6633. Min Act: -0.1700
Data Index: 7192855 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9133. Min Range: -4.9133
Max Act: 4.6320. Min Act: -0.1700
Data Index: 4893678 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9133. Min Range: -4.9133
Max Act: 4.6320. Min Act: -0.1700
Data Index: 2828674 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9133. Min Range: -4.9133
Max Act: 4.6320. Min Act: -0.1700
Data Index: 486152 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #19