Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3927 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.0170. Min Range: -4.0170
Max Act: 4.0170. Min Act: -0.1700
Data Index: 3618428 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0170. Min Range: -4.0170
Max Act: 3.8919. Min Act: -0.1700
Data Index: 8165118 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0170. Min Range: -4.0170
Max Act: 3.8919. Min Act: -0.1700
Data Index: 3942659 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0170. Min Range: -4.0170
Max Act: 3.8919. Min Act: -0.1700
Data Index: 1351630 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0170. Min Range: -4.0170
Max Act: 3.8919. Min Act: -0.1700
Data Index: 5189046 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0170. Min Range: -4.0170
Max Act: 3.8919. Min Act: -0.1700
Data Index: 43905 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0170. Min Range: -4.0170
Max Act: 3.8919. Min Act: -0.1700
Data Index: 4238439 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0170. Min Range: -4.0170
Max Act: 3.8607. Min Act: -0.1700
Data Index: 1293194 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0170. Min Range: -4.0170
Max Act: 3.8607. Min Act: -0.1700
Data Index: 5165075 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0170. Min Range: -4.0170
Max Act: 3.8294. Min Act: -0.1700
Data Index: 2957265 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0170. Min Range: -4.0170
Max Act: 3.8607. Min Act: -0.1699
Data Index: 5497006 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0170. Min Range: -4.0170
Max Act: 3.8607. Min Act: -0.1700
Data Index: 5938316 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0170. Min Range: -4.0170
Max Act: 3.8607. Min Act: -0.1700
Data Index: 6265866 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0170. Min Range: -4.0170
Max Act: 3.8607. Min Act: -0.1700
Data Index: 6337241 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0170. Min Range: -4.0170
Max Act: 3.8607. Min Act: -0.1700
Data Index: 6526849 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0170. Min Range: -4.0170
Max Act: 3.8607. Min Act: -0.1700
Data Index: 3346109 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0170. Min Range: -4.0170
Max Act: 3.8607. Min Act: -0.1700
Data Index: 1884625 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0170. Min Range: -4.0170
Max Act: 3.8607. Min Act: -0.1700
Data Index: 6632677 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0170. Min Range: -4.0170
Max Act: 3.8607. Min Act: -0.1700
Data Index: 7433723 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0170. Min Range: -4.0170
Max Act: 3.8607. Min Act: -0.1700
Data Index: 1980022 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #19