Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2853 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9759. Min Range: -7.9759
Max Act: 7.9759. Min Act: -0.1700
Data Index: 5710139 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9759. Min Range: -7.9759
Max Act: 7.8196. Min Act: -0.1700
Data Index: 4562290 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9759. Min Range: -7.9759
Max Act: 7.6634. Min Act: -0.1700
Data Index: 5859029 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9759. Min Range: -7.9759
Max Act: 7.6009. Min Act: -0.1700
Data Index: 8435195 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9759. Min Range: -7.9759
Max Act: 7.6009. Min Act: -0.1700
Data Index: 8806022 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9759. Min Range: -7.9759
Max Act: 7.5696. Min Act: -0.1700
Data Index: 3745819 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9759. Min Range: -7.9759
Max Act: 7.5071. Min Act: -0.1700
Data Index: 5116827 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9759. Min Range: -7.9759
Max Act: 7.5384. Min Act: -0.1700
Data Index: 8100859 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9759. Min Range: -7.9759
Max Act: 7.5071. Min Act: -0.1700
Data Index: 4250169 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9759. Min Range: -7.9759
Max Act: 7.4759. Min Act: -0.1700
Data Index: 8146602 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9759. Min Range: -7.9759
Max Act: 7.4446. Min Act: -0.1700
Data Index: 8587048 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9759. Min Range: -7.9759
Max Act: 7.4446. Min Act: -0.1700
Data Index: 2145914 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9759. Min Range: -7.9759
Max Act: 7.4134. Min Act: -0.1700
Data Index: 5747396 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9759. Min Range: -7.9759
Max Act: 7.4134. Min Act: -0.1700
Data Index: 860034 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9759. Min Range: -7.9759
Max Act: 7.3821. Min Act: -0.1700
Data Index: 601296 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9759. Min Range: -7.9759
Max Act: 7.3821. Min Act: -0.1700
Data Index: 3309920 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9759. Min Range: -7.9759
Max Act: 7.3509. Min Act: -0.1700
Data Index: 4854299 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9759. Min Range: -7.9759
Max Act: 7.3196. Min Act: -0.1700
Data Index: 6953594 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9759. Min Range: -7.9759
Max Act: 7.2571. Min Act: -0.1700
Data Index: 17598 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9759. Min Range: -7.9759
Max Act: 7.2884. Min Act: -0.1700
Data Index: 5536772 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #19