Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2251 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.6582. Min Range: -10.6582
Max Act: 10.6582. Min Act: -0.1700
Data Index: 7984728 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.6582. Min Range: -10.6582
Max Act: 9.7207. Min Act: -0.1700
Data Index: 1174122 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.6582. Min Range: -10.6582
Max Act: 9.5957. Min Act: -0.1700
Data Index: 1365522 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.6582. Min Range: -10.6582
Max Act: 9.5332. Min Act: -0.1700
Data Index: 5967192 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.6582. Min Range: -10.6582
Max Act: 9.2207. Min Act: -0.1700
Data Index: 4173141 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.6582. Min Range: -10.6582
Max Act: 9.2207. Min Act: -0.1700
Data Index: 1747395 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.6582. Min Range: -10.6582
Max Act: 9.0957. Min Act: -0.1700
Data Index: 670308 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.6582. Min Range: -10.6582
Max Act: 9.1582. Min Act: -0.1700
Data Index: 6693330 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.6582. Min Range: -10.6582
Max Act: 9.0957. Min Act: -0.1700
Data Index: 1042769 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.6582. Min Range: -10.6582
Max Act: 9.0332. Min Act: -0.1700
Data Index: 1371401 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.6582. Min Range: -10.6582
Max Act: 9.0332. Min Act: -0.1700
Data Index: 5656929 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.6582. Min Range: -10.6582
Max Act: 8.9707. Min Act: -0.1700
Data Index: 5955441 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.6582. Min Range: -10.6582
Max Act: 8.9707. Min Act: -0.1700
Data Index: 4426406 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.6582. Min Range: -10.6582
Max Act: 8.9082. Min Act: -0.1700
Data Index: 7869743 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.6582. Min Range: -10.6582
Max Act: 8.9082. Min Act: -0.1700
Data Index: 4089049 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.6582. Min Range: -10.6582
Max Act: 8.7832. Min Act: -0.1700
Data Index: 4519973 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.6582. Min Range: -10.6582
Max Act: 8.8457. Min Act: -0.1700
Data Index: 8619089 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.6582. Min Range: -10.6582
Max Act: 8.8457. Min Act: -0.1700
Data Index: 807447 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.6582. Min Range: -10.6582
Max Act: 8.7832. Min Act: -0.1700
Data Index: 1135673 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.6582. Min Range: -10.6582
Max Act: 8.7832. Min Act: -0.1700
Data Index: 7405188 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #19