Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3640 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7155. Min Range: -7.7155
Max Act: 7.7155. Min Act: -0.1700
Data Index: 4974338 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7155. Min Range: -7.7155
Max Act: 7.4655. Min Act: -0.1700
Data Index: 8531855 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7155. Min Range: -7.7155
Max Act: 7.3717. Min Act: -0.1700
Data Index: 3321377 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7155. Min Range: -7.7155
Max Act: 7.3405. Min Act: -0.1700
Data Index: 401517 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7155. Min Range: -7.7155
Max Act: 7.2780. Min Act: -0.1700
Data Index: 6893818 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7155. Min Range: -7.7155
Max Act: 7.2780. Min Act: -0.1700
Data Index: 6722290 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7155. Min Range: -7.7155
Max Act: 7.2780. Min Act: -0.1700
Data Index: 4531961 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7155. Min Range: -7.7155
Max Act: 7.2780. Min Act: -0.1700
Data Index: 7938781 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7155. Min Range: -7.7155
Max Act: 7.1530. Min Act: -0.1700
Data Index: 8177469 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7155. Min Range: -7.7155
Max Act: 7.1217. Min Act: -0.1700
Data Index: 4424278 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7155. Min Range: -7.7155
Max Act: 7.0592. Min Act: -0.1700
Data Index: 4013025 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7155. Min Range: -7.7155
Max Act: 6.9967. Min Act: -0.1700
Data Index: 6061544 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7155. Min Range: -7.7155
Max Act: 6.9030. Min Act: -0.1700
Data Index: 4749346 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7155. Min Range: -7.7155
Max Act: 6.8405. Min Act: -0.1700
Data Index: 114499 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7155. Min Range: -7.7155
Max Act: 6.8092. Min Act: -0.1700
Data Index: 939707 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7155. Min Range: -7.7155
Max Act: 6.7780. Min Act: -0.1700
Data Index: 7074145 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7155. Min Range: -7.7155
Max Act: 6.7780. Min Act: -0.1700
Data Index: 6646439 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7155. Min Range: -7.7155
Max Act: 6.7780. Min Act: -0.1700
Data Index: 82059 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7155. Min Range: -7.7155
Max Act: 6.7780. Min Act: -0.1700
Data Index: 7120039 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7155. Min Range: -7.7155
Max Act: 6.7467. Min Act: -0.1700
Data Index: 6841930 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #19