Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3389 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4438. Min Range: -8.4438
Max Act: 8.4438. Min Act: -0.1700
Data Index: 1209883 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4438. Min Range: -8.4438
Max Act: 7.9438. Min Act: -0.1700
Data Index: 1316494 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4438. Min Range: -8.4438
Max Act: 7.8813. Min Act: -0.1700
Data Index: 7265106 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4438. Min Range: -8.4438
Max Act: 7.8813. Min Act: -0.1700
Data Index: 6968946 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4438. Min Range: -8.4438
Max Act: 7.7563. Min Act: -0.1700
Data Index: 3943946 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4438. Min Range: -8.4438
Max Act: 7.7563. Min Act: -0.1700
Data Index: 2600905 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4438. Min Range: -8.4438
Max Act: 7.7563. Min Act: -0.1700
Data Index: 1893354 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4438. Min Range: -8.4438
Max Act: 7.6313. Min Act: -0.1700
Data Index: 2798225 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4438. Min Range: -8.4438
Max Act: 7.5688. Min Act: -0.1700
Data Index: 3554820 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4438. Min Range: -8.4438
Max Act: 7.5063. Min Act: -0.1700
Data Index: 3655333 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4438. Min Range: -8.4438
Max Act: 7.5063. Min Act: -0.1700
Data Index: 5677176 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4438. Min Range: -8.4438
Max Act: 7.5063. Min Act: -0.1700
Data Index: 5194534 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4438. Min Range: -8.4438
Max Act: 7.4438. Min Act: -0.1700
Data Index: 2616405 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4438. Min Range: -8.4438
Max Act: 7.4438. Min Act: -0.1700
Data Index: 1603007 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4438. Min Range: -8.4438
Max Act: 7.4438. Min Act: -0.1700
Data Index: 2758643 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4438. Min Range: -8.4438
Max Act: 7.4438. Min Act: -0.1700
Data Index: 2486189 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4438. Min Range: -8.4438
Max Act: 7.4438. Min Act: -0.1700
Data Index: 185888 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4438. Min Range: -8.4438
Max Act: 7.4125. Min Act: -0.1700
Data Index: 4157482 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4438. Min Range: -8.4438
Max Act: 7.3813. Min Act: -0.1700
Data Index: 3501086 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4438. Min Range: -8.4438
Max Act: 7.3813. Min Act: -0.1700
Data Index: 1516670 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #19