Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2702 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6077. Min Range: -7.6077
Max Act: 7.6077. Min Act: -0.1700
Data Index: 1841620 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6077. Min Range: -7.6077
Max Act: 7.5765. Min Act: -0.1700
Data Index: 2180191 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6077. Min Range: -7.6077
Max Act: 7.4202. Min Act: -0.1700
Data Index: 6333862 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6077. Min Range: -7.6077
Max Act: 7.3890. Min Act: -0.1700
Data Index: 3946776 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6077. Min Range: -7.6077
Max Act: 7.3577. Min Act: -0.1700
Data Index: 716515 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6077. Min Range: -7.6077
Max Act: 7.3265. Min Act: -0.1700
Data Index: 1657416 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6077. Min Range: -7.6077
Max Act: 7.2327. Min Act: -0.1700
Data Index: 2459731 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6077. Min Range: -7.6077
Max Act: 7.2015. Min Act: -0.1700
Data Index: 3598514 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6077. Min Range: -7.6077
Max Act: 7.1702. Min Act: -0.1700
Data Index: 965881 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6077. Min Range: -7.6077
Max Act: 7.1390. Min Act: -0.1700
Data Index: 4490931 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6077. Min Range: -7.6077
Max Act: 7.1077. Min Act: -0.1700
Data Index: 1905712 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6077. Min Range: -7.6077
Max Act: 7.0765. Min Act: -0.1700
Data Index: 4385076 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6077. Min Range: -7.6077
Max Act: 7.1077. Min Act: -0.1700
Data Index: 7824848 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6077. Min Range: -7.6077
Max Act: 7.1077. Min Act: -0.1700
Data Index: 6503850 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6077. Min Range: -7.6077
Max Act: 7.1077. Min Act: -0.1700
Data Index: 2083277 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6077. Min Range: -7.6077
Max Act: 7.1077. Min Act: -0.1700
Data Index: 7908199 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6077. Min Range: -7.6077
Max Act: 7.0452. Min Act: -0.1700
Data Index: 3688755 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6077. Min Range: -7.6077
Max Act: 7.0452. Min Act: -0.1700
Data Index: 6712015 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6077. Min Range: -7.6077
Max Act: 6.9827. Min Act: -0.1700
Data Index: 3668577 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6077. Min Range: -7.6077
Max Act: 6.9827. Min Act: -0.1700
Data Index: 3563195 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #19