Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5180 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9821. Min Range: -6.9821
Max Act: 6.9821. Min Act: -0.1700
Data Index: 3772971 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9821. Min Range: -6.9821
Max Act: 6.7946. Min Act: -0.1700
Data Index: 4157306 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9821. Min Range: -6.9821
Max Act: 6.7633. Min Act: -0.1700
Data Index: 6762849 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9821. Min Range: -6.9821
Max Act: 6.7321. Min Act: -0.1700
Data Index: 759252 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9821. Min Range: -6.9821
Max Act: 6.7321. Min Act: -0.1700
Data Index: 1371350 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9821. Min Range: -6.9821
Max Act: 6.7008. Min Act: -0.1700
Data Index: 55134 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9821. Min Range: -6.9821
Max Act: 6.6696. Min Act: -0.1700
Data Index: 459713 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9821. Min Range: -6.9821
Max Act: 6.6696. Min Act: -0.1700
Data Index: 2940631 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9821. Min Range: -6.9821
Max Act: 6.6383. Min Act: -0.1700
Data Index: 8047679 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9821. Min Range: -6.9821
Max Act: 6.6696. Min Act: -0.1700
Data Index: 4526863 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9821. Min Range: -6.9821
Max Act: 6.6071. Min Act: -0.1700
Data Index: 4750236 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9821. Min Range: -6.9821
Max Act: 6.6071. Min Act: -0.1700
Data Index: 2397787 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9821. Min Range: -6.9821
Max Act: 6.5758. Min Act: -0.1700
Data Index: 2396195 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9821. Min Range: -6.9821
Max Act: 6.5446. Min Act: -0.1700
Data Index: 234582 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9821. Min Range: -6.9821
Max Act: 6.5446. Min Act: -0.1700
Data Index: 3269388 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9821. Min Range: -6.9821
Max Act: 6.5446. Min Act: -0.1700
Data Index: 8051696 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9821. Min Range: -6.9821
Max Act: 6.5758. Min Act: -0.1700
Data Index: 323833 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9821. Min Range: -6.9821
Max Act: 6.5133. Min Act: -0.1700
Data Index: 7759945 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9821. Min Range: -6.9821
Max Act: 6.5446. Min Act: -0.1700
Data Index: 6871200 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9821. Min Range: -6.9821
Max Act: 6.5133. Min Act: -0.1700
Data Index: 1907163 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #19