Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 225 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9558. Min Range: -6.9558
Max Act: 6.9558. Min Act: -0.1700
Data Index: 1089673 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9558. Min Range: -6.9558
Max Act: 6.6746. Min Act: -0.1700
Data Index: 866481 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9558. Min Range: -6.9558
Max Act: 6.6121. Min Act: -0.1700
Data Index: 5306207 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9558. Min Range: -6.9558
Max Act: 6.4246. Min Act: -0.1700
Data Index: 4542248 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9558. Min Range: -6.9558
Max Act: 6.3933. Min Act: -0.1700
Data Index: 332903 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9558. Min Range: -6.9558
Max Act: 6.2996. Min Act: -0.1700
Data Index: 725976 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9558. Min Range: -6.9558
Max Act: 6.2371. Min Act: -0.1700
Data Index: 4656949 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9558. Min Range: -6.9558
Max Act: 6.2371. Min Act: -0.1700
Data Index: 6501717 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9558. Min Range: -6.9558
Max Act: 6.2058. Min Act: -0.1700
Data Index: 332363 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9558. Min Range: -6.9558
Max Act: 6.1746. Min Act: -0.1700
Data Index: 7689313 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9558. Min Range: -6.9558
Max Act: 6.1433. Min Act: -0.1700
Data Index: 8404188 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9558. Min Range: -6.9558
Max Act: 6.1433. Min Act: -0.1700
Data Index: 1314683 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9558. Min Range: -6.9558
Max Act: 6.0808. Min Act: -0.1700
Data Index: 7447587 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9558. Min Range: -6.9558
Max Act: 6.0496. Min Act: -0.1700
Data Index: 3210526 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9558. Min Range: -6.9558
Max Act: 6.0183. Min Act: -0.1700
Data Index: 5610366 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9558. Min Range: -6.9558
Max Act: 5.9558. Min Act: -0.1700
Data Index: 4163569 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9558. Min Range: -6.9558
Max Act: 5.9558. Min Act: -0.1700
Data Index: 1081500 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9558. Min Range: -6.9558
Max Act: 5.9558. Min Act: -0.1700
Data Index: 5228940 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9558. Min Range: -6.9558
Max Act: 5.9246. Min Act: -0.1700
Data Index: 3063526 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9558. Min Range: -6.9558
Max Act: 5.9558. Min Act: -0.1700
Data Index: 3174315 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #19