Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1673 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0752. Min Range: -6.0752
Max Act: 6.0752. Min Act: -0.1700
Data Index: 8374778 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0752. Min Range: -6.0752
Max Act: 5.9502. Min Act: -0.1700
Data Index: 4336521 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0752. Min Range: -6.0752
Max Act: 5.9502. Min Act: -0.1700
Data Index: 21977 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0752. Min Range: -6.0752
Max Act: 5.9189. Min Act: -0.1700
Data Index: 1061681 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0752. Min Range: -6.0752
Max Act: 5.8564. Min Act: -0.1700
Data Index: 8262407 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0752. Min Range: -6.0752
Max Act: 5.8877. Min Act: -0.1700
Data Index: 2151053 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0752. Min Range: -6.0752
Max Act: 5.8564. Min Act: -0.1700
Data Index: 8008239 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0752. Min Range: -6.0752
Max Act: 5.8564. Min Act: -0.1700
Data Index: 1441611 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0752. Min Range: -6.0752
Max Act: 5.8564. Min Act: -0.1700
Data Index: 8651274 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0752. Min Range: -6.0752
Max Act: 5.8252. Min Act: -0.1700
Data Index: 8651275 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0752. Min Range: -6.0752
Max Act: 5.8252. Min Act: -0.1700
Data Index: 4995164 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0752. Min Range: -6.0752
Max Act: 5.7939. Min Act: -0.1700
Data Index: 3714643 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0752. Min Range: -6.0752
Max Act: 5.7939. Min Act: -0.1700
Data Index: 2224054 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0752. Min Range: -6.0752
Max Act: 5.7939. Min Act: -0.1700
Data Index: 7879017 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0752. Min Range: -6.0752
Max Act: 5.7939. Min Act: -0.1700
Data Index: 2875819 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0752. Min Range: -6.0752
Max Act: 5.7939. Min Act: -0.1700
Data Index: 7381557 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0752. Min Range: -6.0752
Max Act: 5.7939. Min Act: -0.1700
Data Index: 7355464 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0752. Min Range: -6.0752
Max Act: 5.7939. Min Act: -0.1700
Data Index: 8533110 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0752. Min Range: -6.0752
Max Act: 5.7939. Min Act: -0.1700
Data Index: 5290936 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0752. Min Range: -6.0752
Max Act: 5.7627. Min Act: -0.1700
Data Index: 8033559 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #19