Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5798 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8412. Min Range: -4.8412
Max Act: 4.8412. Min Act: -0.1700
Data Index: 129655 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8412. Min Range: -4.8412
Max Act: 4.7787. Min Act: -0.1700
Data Index: 7234296 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8412. Min Range: -4.8412
Max Act: 4.7475. Min Act: -0.1700
Data Index: 3362251 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8412. Min Range: -4.8412
Max Act: 4.7787. Min Act: -0.1700
Data Index: 7921275 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8412. Min Range: -4.8412
Max Act: 4.7162. Min Act: -0.1700
Data Index: 1410786 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8412. Min Range: -4.8412
Max Act: 4.6850. Min Act: -0.1700
Data Index: 4680770 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8412. Min Range: -4.8412
Max Act: 4.6537. Min Act: -0.1700
Data Index: 1625047 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8412. Min Range: -4.8412
Max Act: 4.6850. Min Act: -0.1700
Data Index: 4927154 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8412. Min Range: -4.8412
Max Act: 4.5600. Min Act: -0.1700
Data Index: 4262913 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8412. Min Range: -4.8412
Max Act: 4.5912. Min Act: -0.1700
Data Index: 1438687 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8412. Min Range: -4.8412
Max Act: 4.5600. Min Act: -0.1700
Data Index: 7232868 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8412. Min Range: -4.8412
Max Act: 4.5600. Min Act: -0.1700
Data Index: 6751312 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8412. Min Range: -4.8412
Max Act: 4.5912. Min Act: -0.1700
Data Index: 4253659 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8412. Min Range: -4.8412
Max Act: 4.5600. Min Act: -0.1700
Data Index: 8547977 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8412. Min Range: -4.8412
Max Act: 4.5287. Min Act: -0.1700
Data Index: 3704790 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8412. Min Range: -4.8412
Max Act: 4.5287. Min Act: -0.1700
Data Index: 2351405 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8412. Min Range: -4.8412
Max Act: 4.5287. Min Act: -0.1700
Data Index: 6005727 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8412. Min Range: -4.8412
Max Act: 4.5287. Min Act: -0.1700
Data Index: 5431598 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8412. Min Range: -4.8412
Max Act: 4.4975. Min Act: -0.1700
Data Index: 4946692 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8412. Min Range: -4.8412
Max Act: 4.4975. Min Act: -0.1700
Data Index: 5001090 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #19