Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3912 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9793. Min Range: -7.9793
Max Act: 7.9793. Min Act: -0.1700
Data Index: 2602381 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9793. Min Range: -7.9793
Max Act: 7.9168. Min Act: -0.1700
Data Index: 636770 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9793. Min Range: -7.9793
Max Act: 7.7918. Min Act: -0.1700
Data Index: 4722019 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9793. Min Range: -7.9793
Max Act: 7.7918. Min Act: -0.1700
Data Index: 4956265 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9793. Min Range: -7.9793
Max Act: 7.7293. Min Act: -0.1700
Data Index: 6732563 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9793. Min Range: -7.9793
Max Act: 7.6668. Min Act: -0.1700
Data Index: 6796031 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9793. Min Range: -7.9793
Max Act: 7.6668. Min Act: -0.1700
Data Index: 2247281 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9793. Min Range: -7.9793
Max Act: 7.6668. Min Act: -0.1700
Data Index: 6041796 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9793. Min Range: -7.9793
Max Act: 7.6668. Min Act: -0.1700
Data Index: 4415805 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9793. Min Range: -7.9793
Max Act: 7.6043. Min Act: -0.1700
Data Index: 4224114 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9793. Min Range: -7.9793
Max Act: 7.6043. Min Act: -0.1700
Data Index: 1079907 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9793. Min Range: -7.9793
Max Act: 7.6043. Min Act: -0.1700
Data Index: 965070 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9793. Min Range: -7.9793
Max Act: 7.5418. Min Act: -0.1700
Data Index: 5487980 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9793. Min Range: -7.9793
Max Act: 7.6043. Min Act: -0.1700
Data Index: 7657220 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9793. Min Range: -7.9793
Max Act: 7.5418. Min Act: -0.1700
Data Index: 3044035 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9793. Min Range: -7.9793
Max Act: 7.5418. Min Act: -0.1700
Data Index: 7813822 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9793. Min Range: -7.9793
Max Act: 7.4793. Min Act: -0.1700
Data Index: 1412680 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9793. Min Range: -7.9793
Max Act: 7.4793. Min Act: -0.1700
Data Index: 5447576 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9793. Min Range: -7.9793
Max Act: 7.4793. Min Act: -0.1700
Data Index: 2139783 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9793. Min Range: -7.9793
Max Act: 7.4793. Min Act: -0.1700
Data Index: 4269790 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #19