Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3045 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6284. Min Range: -7.6284
Max Act: 7.6284. Min Act: -0.1700
Data Index: 3950689 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6284. Min Range: -7.6284
Max Act: 7.5972. Min Act: -0.1700
Data Index: 998587 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6284. Min Range: -7.6284
Max Act: 7.5347. Min Act: -0.1700
Data Index: 7138359 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6284. Min Range: -7.6284
Max Act: 7.4097. Min Act: -0.1700
Data Index: 8062012 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6284. Min Range: -7.6284
Max Act: 7.3159. Min Act: -0.1700
Data Index: 4565270 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6284. Min Range: -7.6284
Max Act: 7.2847. Min Act: -0.1700
Data Index: 7741650 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6284. Min Range: -7.6284
Max Act: 7.2847. Min Act: -0.1700
Data Index: 3400761 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6284. Min Range: -7.6284
Max Act: 7.2534. Min Act: -0.1700
Data Index: 181395 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6284. Min Range: -7.6284
Max Act: 7.2534. Min Act: -0.1700
Data Index: 6985535 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6284. Min Range: -7.6284
Max Act: 7.1909. Min Act: -0.1700
Data Index: 7316128 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6284. Min Range: -7.6284
Max Act: 7.1909. Min Act: -0.1700
Data Index: 2485136 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6284. Min Range: -7.6284
Max Act: 7.1597. Min Act: -0.1700
Data Index: 8099577 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6284. Min Range: -7.6284
Max Act: 7.1284. Min Act: -0.1700
Data Index: 2187747 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6284. Min Range: -7.6284
Max Act: 7.1597. Min Act: -0.1700
Data Index: 4071929 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6284. Min Range: -7.6284
Max Act: 7.1597. Min Act: -0.1700
Data Index: 731906 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6284. Min Range: -7.6284
Max Act: 7.1597. Min Act: -0.1700
Data Index: 3601732 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6284. Min Range: -7.6284
Max Act: 7.1284. Min Act: -0.1700
Data Index: 344493 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6284. Min Range: -7.6284
Max Act: 7.1284. Min Act: -0.1700
Data Index: 3304596 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6284. Min Range: -7.6284
Max Act: 7.1284. Min Act: -0.1700
Data Index: 495465 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6284. Min Range: -7.6284
Max Act: 7.1284. Min Act: -0.1700
Data Index: 6628303 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #19