Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3665 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2766. Min Range: -7.2766
Max Act: 7.2766. Min Act: -0.1700
Data Index: 3543835 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2766. Min Range: -7.2766
Max Act: 7.0891. Min Act: -0.1700
Data Index: 2078791 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2766. Min Range: -7.2766
Max Act: 6.8704. Min Act: -0.1700
Data Index: 2864479 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2766. Min Range: -7.2766
Max Act: 6.8391. Min Act: -0.1700
Data Index: 222973 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2766. Min Range: -7.2766
Max Act: 6.8704. Min Act: -0.1700
Data Index: 2498100 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2766. Min Range: -7.2766
Max Act: 6.8391. Min Act: -0.1700
Data Index: 4501593 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2766. Min Range: -7.2766
Max Act: 6.8391. Min Act: -0.1700
Data Index: 8470911 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2766. Min Range: -7.2766
Max Act: 6.8079. Min Act: -0.1700
Data Index: 4444565 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2766. Min Range: -7.2766
Max Act: 6.7766. Min Act: -0.1700
Data Index: 4535281 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2766. Min Range: -7.2766
Max Act: 6.7766. Min Act: -0.1700
Data Index: 3409235 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2766. Min Range: -7.2766
Max Act: 6.7141. Min Act: -0.1700
Data Index: 6759200 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2766. Min Range: -7.2766
Max Act: 6.7454. Min Act: -0.1700
Data Index: 6055583 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2766. Min Range: -7.2766
Max Act: 6.7141. Min Act: -0.1700
Data Index: 4202291 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2766. Min Range: -7.2766
Max Act: 6.6829. Min Act: -0.1700
Data Index: 1566283 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2766. Min Range: -7.2766
Max Act: 6.6516. Min Act: -0.1700
Data Index: 4006994 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2766. Min Range: -7.2766
Max Act: 6.6204. Min Act: -0.1700
Data Index: 3353737 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2766. Min Range: -7.2766
Max Act: 6.6204. Min Act: -0.1700
Data Index: 3121050 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2766. Min Range: -7.2766
Max Act: 6.6204. Min Act: -0.1700
Data Index: 2285223 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2766. Min Range: -7.2766
Max Act: 6.5891. Min Act: -0.1700
Data Index: 7982350 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2766. Min Range: -7.2766
Max Act: 6.5891. Min Act: -0.1700
Data Index: 4589916 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #19