Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5928 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8127. Min Range: -5.8127
Max Act: 5.8127. Min Act: -0.1700
Data Index: 4238626 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8127. Min Range: -5.8127
Max Act: 5.7815. Min Act: -0.1700
Data Index: 388836 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8127. Min Range: -5.8127
Max Act: 5.6877. Min Act: -0.1700
Data Index: 5787261 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8127. Min Range: -5.8127
Max Act: 5.6565. Min Act: -0.1700
Data Index: 7177048 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8127. Min Range: -5.8127
Max Act: 5.6252. Min Act: -0.1700
Data Index: 255028 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8127. Min Range: -5.8127
Max Act: 5.6252. Min Act: -0.1700
Data Index: 6371904 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8127. Min Range: -5.8127
Max Act: 5.6252. Min Act: -0.1700
Data Index: 5519264 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8127. Min Range: -5.8127
Max Act: 5.6252. Min Act: -0.1700
Data Index: 2674530 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8127. Min Range: -5.8127
Max Act: 5.5940. Min Act: -0.1700
Data Index: 388826 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8127. Min Range: -5.8127
Max Act: 5.5940. Min Act: -0.1700
Data Index: 20168 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8127. Min Range: -5.8127
Max Act: 5.5940. Min Act: -0.1700
Data Index: 6364770 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8127. Min Range: -5.8127
Max Act: 5.5940. Min Act: -0.1700
Data Index: 5648922 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8127. Min Range: -5.8127
Max Act: 5.5940. Min Act: -0.1700
Data Index: 1280310 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8127. Min Range: -5.8127
Max Act: 5.5940. Min Act: -0.1700
Data Index: 433124 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8127. Min Range: -5.8127
Max Act: 5.5627. Min Act: -0.1700
Data Index: 3163416 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8127. Min Range: -5.8127
Max Act: 5.5627. Min Act: -0.1700
Data Index: 5939151 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8127. Min Range: -5.8127
Max Act: 5.5627. Min Act: -0.1700
Data Index: 6155233 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8127. Min Range: -5.8127
Max Act: 5.5627. Min Act: -0.1700
Data Index: 2130155 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8127. Min Range: -5.8127
Max Act: 5.5627. Min Act: -0.1700
Data Index: 4238627 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8127. Min Range: -5.8127
Max Act: 5.5627. Min Act: -0.1700
Data Index: 5486093 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #19