Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 634 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3063. Min Range: -5.3063
Max Act: 5.3063. Min Act: -0.1700
Data Index: 7200569 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3063. Min Range: -5.3063
Max Act: 4.9938. Min Act: -0.1700
Data Index: 992604 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3063. Min Range: -5.3063
Max Act: 4.9938. Min Act: -0.1700
Data Index: 5884162 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3063. Min Range: -5.3063
Max Act: 4.9001. Min Act: -0.1700
Data Index: 391956 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3063. Min Range: -5.3063
Max Act: 4.8688. Min Act: -0.1700
Data Index: 4979066 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3063. Min Range: -5.3063
Max Act: 4.8688. Min Act: -0.1700
Data Index: 6873482 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3063. Min Range: -5.3063
Max Act: 4.8376. Min Act: -0.1700
Data Index: 3770370 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3063. Min Range: -5.3063
Max Act: 4.8063. Min Act: -0.1700
Data Index: 4997151 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3063. Min Range: -5.3063
Max Act: 4.7438. Min Act: -0.1700
Data Index: 7707432 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3063. Min Range: -5.3063
Max Act: 4.6813. Min Act: -0.1700
Data Index: 1536058 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3063. Min Range: -5.3063
Max Act: 4.7126. Min Act: -0.1700
Data Index: 7004343 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3063. Min Range: -5.3063
Max Act: 4.7126. Min Act: -0.1700
Data Index: 949072 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3063. Min Range: -5.3063
Max Act: 4.7438. Min Act: -0.1700
Data Index: 5133706 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3063. Min Range: -5.3063
Max Act: 4.7126. Min Act: -0.1700
Data Index: 2692083 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3063. Min Range: -5.3063
Max Act: 4.7126. Min Act: -0.1700
Data Index: 184170 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3063. Min Range: -5.3063
Max Act: 4.7126. Min Act: -0.1700
Data Index: 3953292 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3063. Min Range: -5.3063
Max Act: 4.6813. Min Act: -0.1700
Data Index: 2065902 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3063. Min Range: -5.3063
Max Act: 4.7126. Min Act: -0.1700
Data Index: 6479174 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3063. Min Range: -5.3063
Max Act: 4.6813. Min Act: -0.1700
Data Index: 3233727 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3063. Min Range: -5.3063
Max Act: 4.6813. Min Act: -0.1700
Data Index: 3837143 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #19