Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2931 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2067. Min Range: -7.2067
Max Act: 7.2067. Min Act: -0.1700
Data Index: 6215078 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2067. Min Range: -7.2067
Max Act: 7.0504. Min Act: -0.1700
Data Index: 7412666 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2067. Min Range: -7.2067
Max Act: 7.0504. Min Act: -0.1700
Data Index: 3680807 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2067. Min Range: -7.2067
Max Act: 6.9879. Min Act: -0.1700
Data Index: 4465592 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2067. Min Range: -7.2067
Max Act: 6.9567. Min Act: -0.1700
Data Index: 6815029 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2067. Min Range: -7.2067
Max Act: 6.9567. Min Act: -0.1700
Data Index: 2495838 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2067. Min Range: -7.2067
Max Act: 6.8942. Min Act: -0.1700
Data Index: 8068403 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2067. Min Range: -7.2067
Max Act: 6.8942. Min Act: -0.1700
Data Index: 602312 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2067. Min Range: -7.2067
Max Act: 6.8629. Min Act: -0.1700
Data Index: 4196333 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2067. Min Range: -7.2067
Max Act: 6.8004. Min Act: -0.1700
Data Index: 3622930 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2067. Min Range: -7.2067
Max Act: 6.8004. Min Act: -0.1700
Data Index: 1793510 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2067. Min Range: -7.2067
Max Act: 6.8004. Min Act: -0.1700
Data Index: 8765544 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2067. Min Range: -7.2067
Max Act: 6.8004. Min Act: -0.1700
Data Index: 2734296 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2067. Min Range: -7.2067
Max Act: 6.7692. Min Act: -0.1700
Data Index: 2921879 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2067. Min Range: -7.2067
Max Act: 6.7692. Min Act: -0.1700
Data Index: 8668174 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2067. Min Range: -7.2067
Max Act: 6.7067. Min Act: -0.1700
Data Index: 6983427 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2067. Min Range: -7.2067
Max Act: 6.7692. Min Act: -0.1700
Data Index: 6489110 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2067. Min Range: -7.2067
Max Act: 6.7379. Min Act: -0.1700
Data Index: 6745053 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2067. Min Range: -7.2067
Max Act: 6.7379. Min Act: -0.1700
Data Index: 8011155 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2067. Min Range: -7.2067
Max Act: 6.7067. Min Act: -0.1700
Data Index: 3301233 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #19