Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3681 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7131. Min Range: -7.7131
Max Act: 7.7131. Min Act: -0.1700
Data Index: 3299349 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7131. Min Range: -7.7131
Max Act: 7.6506. Min Act: -0.1700
Data Index: 2103987 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7131. Min Range: -7.7131
Max Act: 7.5256. Min Act: -0.1700
Data Index: 1804842 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7131. Min Range: -7.7131
Max Act: 7.4006. Min Act: -0.1700
Data Index: 8129986 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7131. Min Range: -7.7131
Max Act: 7.3068. Min Act: -0.1700
Data Index: 8658777 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7131. Min Range: -7.7131
Max Act: 7.3068. Min Act: -0.1700
Data Index: 8065668 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7131. Min Range: -7.7131
Max Act: 7.2756. Min Act: -0.1700
Data Index: 3346897 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7131. Min Range: -7.7131
Max Act: 7.2756. Min Act: -0.1700
Data Index: 5968717 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7131. Min Range: -7.7131
Max Act: 7.2131. Min Act: -0.1700
Data Index: 7451428 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7131. Min Range: -7.7131
Max Act: 7.2443. Min Act: -0.1700
Data Index: 5700574 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7131. Min Range: -7.7131
Max Act: 7.1818. Min Act: -0.1700
Data Index: 1277813 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7131. Min Range: -7.7131
Max Act: 7.1818. Min Act: -0.1700
Data Index: 3994570 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7131. Min Range: -7.7131
Max Act: 7.1818. Min Act: -0.1700
Data Index: 4258718 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7131. Min Range: -7.7131
Max Act: 7.1506. Min Act: -0.1700
Data Index: 5575121 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7131. Min Range: -7.7131
Max Act: 7.1193. Min Act: -0.1700
Data Index: 3188752 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7131. Min Range: -7.7131
Max Act: 7.1193. Min Act: -0.1700
Data Index: 8638579 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7131. Min Range: -7.7131
Max Act: 7.0881. Min Act: -0.1700
Data Index: 7882732 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7131. Min Range: -7.7131
Max Act: 7.1193. Min Act: -0.1700
Data Index: 5605272 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7131. Min Range: -7.7131
Max Act: 7.0568. Min Act: -0.1700
Data Index: 7798024 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7131. Min Range: -7.7131
Max Act: 7.0568. Min Act: -0.1700
Data Index: 3395157 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #19