Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3526 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0926. Min Range: -4.0926
Max Act: 4.0926. Min Act: -0.1700
Data Index: 4602644 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0926. Min Range: -4.0926
Max Act: 3.8738. Min Act: -0.1700
Data Index: 2397383 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0926. Min Range: -4.0926
Max Act: 3.8738. Min Act: -0.1700
Data Index: 4684421 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0926. Min Range: -4.0926
Max Act: 3.8738. Min Act: -0.1700
Data Index: 1925320 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0926. Min Range: -4.0926
Max Act: 3.8425. Min Act: -0.1700
Data Index: 7354606 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0926. Min Range: -4.0926
Max Act: 3.8425. Min Act: -0.1700
Data Index: 6810763 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0926. Min Range: -4.0926
Max Act: 3.8425. Min Act: -0.1700
Data Index: 2886109 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0926. Min Range: -4.0926
Max Act: 3.8113. Min Act: -0.1700
Data Index: 7020163 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0926. Min Range: -4.0926
Max Act: 3.8113. Min Act: -0.1700
Data Index: 6092534 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0926. Min Range: -4.0926
Max Act: 3.7800. Min Act: -0.1700
Data Index: 5134236 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0926. Min Range: -4.0926
Max Act: 3.7487. Min Act: -0.1700
Data Index: 2379967 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0926. Min Range: -4.0926
Max Act: 3.7800. Min Act: -0.1700
Data Index: 2825295 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0926. Min Range: -4.0926
Max Act: 3.8113. Min Act: -0.1700
Data Index: 969059 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0926. Min Range: -4.0926
Max Act: 3.7487. Min Act: -0.1700
Data Index: 7861172 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0926. Min Range: -4.0926
Max Act: 3.7487. Min Act: -0.1700
Data Index: 2712884 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0926. Min Range: -4.0926
Max Act: 3.7800. Min Act: -0.1700
Data Index: 3794215 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0926. Min Range: -4.0926
Max Act: 3.7487. Min Act: -0.1700
Data Index: 774684 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0926. Min Range: -4.0926
Max Act: 3.7487. Min Act: -0.1700
Data Index: 2324285 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0926. Min Range: -4.0926
Max Act: 3.7174. Min Act: -0.1700
Data Index: 455065 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0926. Min Range: -4.0926
Max Act: 3.7487. Min Act: -0.1700
Data Index: 4028852 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #19