Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4078 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6167. Min Range: -5.6167
Max Act: 5.6167. Min Act: -0.1700
Data Index: 3334714 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6167. Min Range: -5.6167
Max Act: 5.2730. Min Act: -0.1700
Data Index: 2353583 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6167. Min Range: -5.6167
Max Act: 5.2105. Min Act: -0.1700
Data Index: 922139 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6167. Min Range: -5.6167
Max Act: 5.1167. Min Act: -0.1700
Data Index: 2940242 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6167. Min Range: -5.6167
Max Act: 4.9917. Min Act: -0.1700
Data Index: 2844883 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6167. Min Range: -5.6167
Max Act: 4.9917. Min Act: -0.1700
Data Index: 6146585 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6167. Min Range: -5.6167
Max Act: 4.9605. Min Act: -0.1700
Data Index: 3167470 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6167. Min Range: -5.6167
Max Act: 4.9605. Min Act: -0.1700
Data Index: 5206872 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6167. Min Range: -5.6167
Max Act: 4.9605. Min Act: -0.1700
Data Index: 444213 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6167. Min Range: -5.6167
Max Act: 4.9292. Min Act: -0.1700
Data Index: 3500632 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6167. Min Range: -5.6167
Max Act: 4.9292. Min Act: -0.1700
Data Index: 5248522 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6167. Min Range: -5.6167
Max Act: 4.9292. Min Act: -0.1700
Data Index: 8625245 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6167. Min Range: -5.6167
Max Act: 4.8980. Min Act: -0.1700
Data Index: 286857 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6167. Min Range: -5.6167
Max Act: 4.8980. Min Act: -0.1700
Data Index: 2320005 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6167. Min Range: -5.6167
Max Act: 4.8667. Min Act: -0.1700
Data Index: 3876250 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6167. Min Range: -5.6167
Max Act: 4.8667. Min Act: -0.1700
Data Index: 4590887 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6167. Min Range: -5.6167
Max Act: 4.8667. Min Act: -0.1700
Data Index: 1485343 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6167. Min Range: -5.6167
Max Act: 4.8667. Min Act: -0.1700
Data Index: 4278929 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6167. Min Range: -5.6167
Max Act: 4.8980. Min Act: -0.1700
Data Index: 8280940 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6167. Min Range: -5.6167
Max Act: 4.8667. Min Act: -0.1700
Data Index: 2219060 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #19