Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3204 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9693. Min Range: -5.9693
Max Act: 5.9693. Min Act: -0.1700
Data Index: 7507234 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9693. Min Range: -5.9693
Max Act: 5.9693. Min Act: -0.1700
Data Index: 5986320 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9693. Min Range: -5.9693
Max Act: 5.9068. Min Act: -0.1700
Data Index: 1856074 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9693. Min Range: -5.9693
Max Act: 5.9068. Min Act: -0.1700
Data Index: 2837418 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9693. Min Range: -5.9693
Max Act: 5.8755. Min Act: -0.1700
Data Index: 4999517 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9693. Min Range: -5.9693
Max Act: 5.8443. Min Act: -0.1700
Data Index: 7642191 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9693. Min Range: -5.9693
Max Act: 5.8443. Min Act: -0.1700
Data Index: 4685120 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9693. Min Range: -5.9693
Max Act: 5.8443. Min Act: -0.1700
Data Index: 1517638 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9693. Min Range: -5.9693
Max Act: 5.7505. Min Act: -0.1700
Data Index: 7138090 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9693. Min Range: -5.9693
Max Act: 5.7818. Min Act: -0.1700
Data Index: 8290897 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9693. Min Range: -5.9693
Max Act: 5.7505. Min Act: -0.1700
Data Index: 3642156 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9693. Min Range: -5.9693
Max Act: 5.7505. Min Act: -0.1700
Data Index: 2226181 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9693. Min Range: -5.9693
Max Act: 5.7818. Min Act: -0.1700
Data Index: 8610607 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9693. Min Range: -5.9693
Max Act: 5.7193. Min Act: -0.1700
Data Index: 5934633 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9693. Min Range: -5.9693
Max Act: 5.7193. Min Act: -0.1700
Data Index: 7607550 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9693. Min Range: -5.9693
Max Act: 5.7193. Min Act: -0.1700
Data Index: 8581590 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9693. Min Range: -5.9693
Max Act: 5.7193. Min Act: -0.1700
Data Index: 2006158 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9693. Min Range: -5.9693
Max Act: 5.7193. Min Act: -0.1700
Data Index: 5293701 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9693. Min Range: -5.9693
Max Act: 5.6880. Min Act: -0.1700
Data Index: 614758 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9693. Min Range: -5.9693
Max Act: 5.6880. Min Act: -0.1700
Data Index: 1765424 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #19