Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6370 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7162. Min Range: -3.7162
Max Act: 3.7162. Min Act: -0.1700
Data Index: 2502157 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7162. Min Range: -3.7162
Max Act: 3.7006. Min Act: -0.1700
Data Index: 4917276 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7162. Min Range: -3.7162
Max Act: 3.6693. Min Act: -0.1700
Data Index: 432894 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7162. Min Range: -3.7162
Max Act: 3.6693. Min Act: -0.1700
Data Index: 4396239 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7162. Min Range: -3.7162
Max Act: 3.6850. Min Act: -0.1700
Data Index: 8368418 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7162. Min Range: -3.7162
Max Act: 3.6850. Min Act: -0.1700
Data Index: 1864704 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7162. Min Range: -3.7162
Max Act: 3.6537. Min Act: -0.1700
Data Index: 8448673 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7162. Min Range: -3.7162
Max Act: 3.6224. Min Act: -0.1700
Data Index: 1491368 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7162. Min Range: -3.7162
Max Act: 3.6380. Min Act: -0.1700
Data Index: 85783 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7162. Min Range: -3.7162
Max Act: 3.6224. Min Act: -0.1700
Data Index: 7542939 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7162. Min Range: -3.7162
Max Act: 3.6380. Min Act: -0.1700
Data Index: 5371740 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7162. Min Range: -3.7162
Max Act: 3.5911. Min Act: -0.1700
Data Index: 3068828 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7162. Min Range: -3.7162
Max Act: 3.6067. Min Act: -0.1700
Data Index: 8408138 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7162. Min Range: -3.7162
Max Act: 3.6067. Min Act: -0.1700
Data Index: 5812887 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7162. Min Range: -3.7162
Max Act: 3.5754. Min Act: -0.1700
Data Index: 5997701 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7162. Min Range: -3.7162
Max Act: 3.5911. Min Act: -0.1700
Data Index: 4456936 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7162. Min Range: -3.7162
Max Act: 3.5598. Min Act: -0.1700
Data Index: 1993309 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7162. Min Range: -3.7162
Max Act: 3.5754. Min Act: -0.1700
Data Index: 6836629 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7162. Min Range: -3.7162
Max Act: 3.5754. Min Act: -0.1700
Data Index: 4995982 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7162. Min Range: -3.7162
Max Act: 3.5441. Min Act: -0.1700
Data Index: 1941361 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #19