Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3696 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8093. Min Range: -4.8093
Max Act: 4.8093. Min Act: -0.1700
Data Index: 782062 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8093. Min Range: -4.8093
Max Act: 4.7781. Min Act: -0.1700
Data Index: 5580721 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8093. Min Range: -4.8093
Max Act: 4.7781. Min Act: -0.1700
Data Index: 1307467 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8093. Min Range: -4.8093
Max Act: 4.7781. Min Act: -0.1700
Data Index: 5518003 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8093. Min Range: -4.8093
Max Act: 4.7468. Min Act: -0.1700
Data Index: 794057 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8093. Min Range: -4.8093
Max Act: 4.7156. Min Act: -0.1700
Data Index: 5593469 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8093. Min Range: -4.8093
Max Act: 4.6843. Min Act: -0.1700
Data Index: 2004846 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8093. Min Range: -4.8093
Max Act: 4.6843. Min Act: -0.1700
Data Index: 6434062 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8093. Min Range: -4.8093
Max Act: 4.6843. Min Act: -0.1700
Data Index: 4351321 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8093. Min Range: -4.8093
Max Act: 4.6531. Min Act: -0.1700
Data Index: 2786697 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8093. Min Range: -4.8093
Max Act: 4.7156. Min Act: -0.1700
Data Index: 6374376 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8093. Min Range: -4.8093
Max Act: 4.6531. Min Act: -0.1700
Data Index: 5025632 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8093. Min Range: -4.8093
Max Act: 4.6531. Min Act: -0.1700
Data Index: 2190686 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8093. Min Range: -4.8093
Max Act: 4.6531. Min Act: -0.1700
Data Index: 3379888 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8093. Min Range: -4.8093
Max Act: 4.6218. Min Act: -0.1700
Data Index: 217237 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8093. Min Range: -4.8093
Max Act: 4.6218. Min Act: -0.1700
Data Index: 6574002 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8093. Min Range: -4.8093
Max Act: 4.6218. Min Act: -0.1700
Data Index: 7947111 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8093. Min Range: -4.8093
Max Act: 4.5906. Min Act: -0.1700
Data Index: 3349005 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8093. Min Range: -4.8093
Max Act: 4.6218. Min Act: -0.1700
Data Index: 3641200 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8093. Min Range: -4.8093
Max Act: 4.5906. Min Act: -0.1700
Data Index: 1568458 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #19