Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2066 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8285. Min Range: -7.8285
Max Act: 7.8285. Min Act: -0.1700
Data Index: 8073375 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8285. Min Range: -7.8285
Max Act: 7.5785. Min Act: -0.1700
Data Index: 1353765 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8285. Min Range: -7.8285
Max Act: 7.3598. Min Act: -0.1700
Data Index: 4970482 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8285. Min Range: -7.8285
Max Act: 7.3598. Min Act: -0.1700
Data Index: 3250248 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8285. Min Range: -7.8285
Max Act: 7.2973. Min Act: -0.1700
Data Index: 2902807 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8285. Min Range: -7.8285
Max Act: 7.3285. Min Act: -0.1700
Data Index: 4814641 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8285. Min Range: -7.8285
Max Act: 7.2973. Min Act: -0.1700
Data Index: 7783549 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8285. Min Range: -7.8285
Max Act: 7.2660. Min Act: -0.1700
Data Index: 2308274 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8285. Min Range: -7.8285
Max Act: 7.3598. Min Act: -0.1700
Data Index: 8442993 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8285. Min Range: -7.8285
Max Act: 7.2660. Min Act: -0.1700
Data Index: 827418 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8285. Min Range: -7.8285
Max Act: 7.2973. Min Act: -0.1700
Data Index: 6355759 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8285. Min Range: -7.8285
Max Act: 7.2348. Min Act: -0.1700
Data Index: 8624415 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8285. Min Range: -7.8285
Max Act: 7.2035. Min Act: -0.1700
Data Index: 8828474 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8285. Min Range: -7.8285
Max Act: 7.2035. Min Act: -0.1700
Data Index: 1467392 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8285. Min Range: -7.8285
Max Act: 7.2348. Min Act: -0.1700
Data Index: 5032882 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8285. Min Range: -7.8285
Max Act: 7.2035. Min Act: -0.1700
Data Index: 2549071 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8285. Min Range: -7.8285
Max Act: 7.2035. Min Act: -0.1700
Data Index: 6656978 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8285. Min Range: -7.8285
Max Act: 7.2035. Min Act: -0.1700
Data Index: 8041942 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8285. Min Range: -7.8285
Max Act: 7.2035. Min Act: -0.1700
Data Index: 944721 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8285. Min Range: -7.8285
Max Act: 7.2035. Min Act: -0.1700
Data Index: 3505752 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #19