Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2764 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.8219. Min Range: -2.8219
Max Act: 2.8219. Min Act: -0.1700
Data Index: 213895 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8219. Min Range: -2.8219
Max Act: 2.8059. Min Act: -0.1700
Data Index: 8272718 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8219. Min Range: -2.8219
Max Act: 2.7262. Min Act: -0.1700
Data Index: 7350078 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8219. Min Range: -2.8219
Max Act: 2.7262. Min Act: -0.1700
Data Index: 6580602 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8219. Min Range: -2.8219
Max Act: 2.7262. Min Act: -0.1700
Data Index: 5822597 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8219. Min Range: -2.8219
Max Act: 2.7262. Min Act: -0.1700
Data Index: 7198823 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8219. Min Range: -2.8219
Max Act: 2.7102. Min Act: -0.1700
Data Index: 89999 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8219. Min Range: -2.8219
Max Act: 2.7102. Min Act: -0.1700
Data Index: 8217020 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8219. Min Range: -2.8219
Max Act: 2.6622. Min Act: -0.1700
Data Index: 743360 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8219. Min Range: -2.8219
Max Act: 2.6622. Min Act: -0.1700
Data Index: 7350077 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8219. Min Range: -2.8219
Max Act: 2.6622. Min Act: -0.1700
Data Index: 8093122 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8219. Min Range: -2.8219
Max Act: 2.6622. Min Act: -0.1700
Data Index: 478118 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8219. Min Range: -2.8219
Max Act: 2.6622. Min Act: -0.1700
Data Index: 90005 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8219. Min Range: -2.8219
Max Act: 2.6622. Min Act: -0.1700
Data Index: 4851335 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8219. Min Range: -2.8219
Max Act: 2.6622. Min Act: -0.1700
Data Index: 4607050 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8219. Min Range: -2.8219
Max Act: 2.6461. Min Act: -0.1700
Data Index: 4607049 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8219. Min Range: -2.8219
Max Act: 2.6461. Min Act: -0.1700
Data Index: 221917 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8219. Min Range: -2.8219
Max Act: 2.6461. Min Act: -0.1700
Data Index: 7740253 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8219. Min Range: -2.8219
Max Act: 2.6461. Min Act: -0.1700
Data Index: 3472978 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8219. Min Range: -2.8219
Max Act: 2.6140. Min Act: -0.1700
Data Index: 1081894 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #19