Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2483 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9075. Min Range: -5.9075
Max Act: 5.9075. Min Act: -0.1700
Data Index: 5790854 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9075. Min Range: -5.9075
Max Act: 5.5950. Min Act: -0.1700
Data Index: 2998791 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9075. Min Range: -5.9075
Max Act: 5.5637. Min Act: -0.1700
Data Index: 6679412 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9075. Min Range: -5.9075
Max Act: 5.4075. Min Act: -0.1700
Data Index: 211329 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9075. Min Range: -5.9075
Max Act: 5.2825. Min Act: -0.1700
Data Index: 7146452 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9075. Min Range: -5.9075
Max Act: 5.3137. Min Act: -0.1700
Data Index: 786578 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9075. Min Range: -5.9075
Max Act: 5.3137. Min Act: -0.1700
Data Index: 6182804 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9075. Min Range: -5.9075
Max Act: 5.2825. Min Act: -0.1700
Data Index: 5170665 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9075. Min Range: -5.9075
Max Act: 5.2825. Min Act: -0.1700
Data Index: 7797966 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9075. Min Range: -5.9075
Max Act: 5.2825. Min Act: -0.1700
Data Index: 7268911 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9075. Min Range: -5.9075
Max Act: 5.2512. Min Act: -0.1700
Data Index: 7903120 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9075. Min Range: -5.9075
Max Act: 5.2200. Min Act: -0.1700
Data Index: 1143223 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9075. Min Range: -5.9075
Max Act: 5.2200. Min Act: -0.1700
Data Index: 1467317 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9075. Min Range: -5.9075
Max Act: 5.1575. Min Act: -0.1700
Data Index: 5815877 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9075. Min Range: -5.9075
Max Act: 5.1887. Min Act: -0.1700
Data Index: 5894714 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9075. Min Range: -5.9075
Max Act: 5.1575. Min Act: -0.1700
Data Index: 7796634 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9075. Min Range: -5.9075
Max Act: 5.1575. Min Act: -0.1700
Data Index: 2108648 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9075. Min Range: -5.9075
Max Act: 5.1575. Min Act: -0.1700
Data Index: 642704 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9075. Min Range: -5.9075
Max Act: 5.1575. Min Act: -0.1700
Data Index: 4451308 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9075. Min Range: -5.9075
Max Act: 5.1575. Min Act: -0.1700
Data Index: 7299442 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #19