Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5549 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3801. Min Range: -6.3801
Max Act: 6.3801. Min Act: -0.1700
Data Index: 2049857 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3801. Min Range: -6.3801
Max Act: 6.3488. Min Act: -0.1700
Data Index: 6091936 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3801. Min Range: -6.3801
Max Act: 6.2238. Min Act: -0.1700
Data Index: 3620086 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3801. Min Range: -6.3801
Max Act: 6.0363. Min Act: -0.1700
Data Index: 977645 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3801. Min Range: -6.3801
Max Act: 6.0363. Min Act: -0.1700
Data Index: 2536865 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3801. Min Range: -6.3801
Max Act: 6.0363. Min Act: -0.1700
Data Index: 4110600 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3801. Min Range: -6.3801
Max Act: 6.0363. Min Act: -0.1700
Data Index: 1147627 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3801. Min Range: -6.3801
Max Act: 6.0051. Min Act: -0.1700
Data Index: 7136727 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3801. Min Range: -6.3801
Max Act: 5.9738. Min Act: -0.1700
Data Index: 84965 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3801. Min Range: -6.3801
Max Act: 5.9738. Min Act: -0.1700
Data Index: 8095008 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3801. Min Range: -6.3801
Max Act: 5.9738. Min Act: -0.1700
Data Index: 3652680 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3801. Min Range: -6.3801
Max Act: 5.9113. Min Act: -0.1700
Data Index: 6507874 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3801. Min Range: -6.3801
Max Act: 5.9426. Min Act: -0.1700
Data Index: 5723670 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3801. Min Range: -6.3801
Max Act: 5.8801. Min Act: -0.1700
Data Index: 5169967 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3801. Min Range: -6.3801
Max Act: 5.8801. Min Act: -0.1700
Data Index: 2578376 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3801. Min Range: -6.3801
Max Act: 5.8488. Min Act: -0.1700
Data Index: 4020388 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3801. Min Range: -6.3801
Max Act: 5.8488. Min Act: -0.1700
Data Index: 3423428 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3801. Min Range: -6.3801
Max Act: 5.8176. Min Act: -0.1700
Data Index: 291803 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3801. Min Range: -6.3801
Max Act: 5.8176. Min Act: -0.1700
Data Index: 1138769 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3801. Min Range: -6.3801
Max Act: 5.7863. Min Act: -0.1700
Data Index: 1410027 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #19