Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6399 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1057. Min Range: -6.1057
Max Act: 6.1057. Min Act: -0.1700
Data Index: 5057159 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1057. Min Range: -6.1057
Max Act: 5.9494. Min Act: -0.1700
Data Index: 1700132 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1057. Min Range: -6.1057
Max Act: 5.8244. Min Act: -0.1700
Data Index: 8440246 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1057. Min Range: -6.1057
Max Act: 5.7619. Min Act: -0.1700
Data Index: 2861152 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1057. Min Range: -6.1057
Max Act: 5.7307. Min Act: -0.1700
Data Index: 8811221 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1057. Min Range: -6.1057
Max Act: 5.7619. Min Act: -0.1700
Data Index: 7638033 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1057. Min Range: -6.1057
Max Act: 5.7619. Min Act: -0.1700
Data Index: 7670365 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1057. Min Range: -6.1057
Max Act: 5.6994. Min Act: -0.1700
Data Index: 1450617 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1057. Min Range: -6.1057
Max Act: 5.6994. Min Act: -0.1700
Data Index: 8386633 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1057. Min Range: -6.1057
Max Act: 5.6994. Min Act: -0.1700
Data Index: 8366666 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1057. Min Range: -6.1057
Max Act: 5.6369. Min Act: -0.1700
Data Index: 4837881 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1057. Min Range: -6.1057
Max Act: 5.6682. Min Act: -0.1700
Data Index: 374039 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1057. Min Range: -6.1057
Max Act: 5.6682. Min Act: -0.1700
Data Index: 786199 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1057. Min Range: -6.1057
Max Act: 5.6682. Min Act: -0.1700
Data Index: 6893941 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1057. Min Range: -6.1057
Max Act: 5.6369. Min Act: -0.1700
Data Index: 5204169 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1057. Min Range: -6.1057
Max Act: 5.6369. Min Act: -0.1700
Data Index: 4400759 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1057. Min Range: -6.1057
Max Act: 5.6057. Min Act: -0.1700
Data Index: 4439670 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1057. Min Range: -6.1057
Max Act: 5.6057. Min Act: -0.1700
Data Index: 6742870 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1057. Min Range: -6.1057
Max Act: 5.6057. Min Act: -0.1700
Data Index: 202420 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1057. Min Range: -6.1057
Max Act: 5.5744. Min Act: -0.1700
Data Index: 4593670 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #19