Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2425 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2453. Min Range: -4.2453
Max Act: 4.2453. Min Act: -0.1700
Data Index: 7151594 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2453. Min Range: -4.2453
Max Act: 4.2141. Min Act: -0.1700
Data Index: 4731146 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2453. Min Range: -4.2453
Max Act: 4.1516. Min Act: -0.1700
Data Index: 389957 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2453. Min Range: -4.2453
Max Act: 4.1203. Min Act: -0.1700
Data Index: 3965826 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2453. Min Range: -4.2453
Max Act: 4.0265. Min Act: -0.1700
Data Index: 3580962 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2453. Min Range: -4.2453
Max Act: 4.0578. Min Act: -0.1700
Data Index: 2764282 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2453. Min Range: -4.2453
Max Act: 4.0265. Min Act: -0.1700
Data Index: 4796952 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2453. Min Range: -4.2453
Max Act: 4.0265. Min Act: -0.1700
Data Index: 4652800 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2453. Min Range: -4.2453
Max Act: 3.9640. Min Act: -0.1700
Data Index: 5751257 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2453. Min Range: -4.2453
Max Act: 3.9328. Min Act: -0.1700
Data Index: 6162282 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2453. Min Range: -4.2453
Max Act: 3.9328. Min Act: -0.1700
Data Index: 3684578 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2453. Min Range: -4.2453
Max Act: 3.9328. Min Act: -0.1700
Data Index: 2634091 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2453. Min Range: -4.2453
Max Act: 3.9015. Min Act: -0.1700
Data Index: 2963391 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2453. Min Range: -4.2453
Max Act: 3.8390. Min Act: -0.1700
Data Index: 6237617 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2453. Min Range: -4.2453
Max Act: 3.8390. Min Act: -0.1700
Data Index: 2945482 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2453. Min Range: -4.2453
Max Act: 3.8077. Min Act: -0.1700
Data Index: 4973791 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2453. Min Range: -4.2453
Max Act: 3.8077. Min Act: -0.1700
Data Index: 6694934 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2453. Min Range: -4.2453
Max Act: 3.8077. Min Act: -0.1700
Data Index: 3645553 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2453. Min Range: -4.2453
Max Act: 3.8077. Min Act: -0.1700
Data Index: 3098971 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2453. Min Range: -4.2453
Max Act: 3.8077. Min Act: -0.1700
Data Index: 4853049 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #19