Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2073 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.5249. Min Range: -5.5249
Max Act: 5.5249. Min Act: -0.1700
Data Index: 4490572 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5249. Min Range: -5.5249
Max Act: 5.3687. Min Act: -0.1700
Data Index: 7614098 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5249. Min Range: -5.5249
Max Act: 5.3062. Min Act: -0.1700
Data Index: 2288485 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5249. Min Range: -5.5249
Max Act: 5.2749. Min Act: -0.1700
Data Index: 3583265 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5249. Min Range: -5.5249
Max Act: 5.2749. Min Act: -0.1700
Data Index: 1640813 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5249. Min Range: -5.5249
Max Act: 5.2749. Min Act: -0.1700
Data Index: 5491182 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5249. Min Range: -5.5249
Max Act: 5.2437. Min Act: -0.1700
Data Index: 6048627 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5249. Min Range: -5.5249
Max Act: 5.2437. Min Act: -0.1700
Data Index: 6098328 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5249. Min Range: -5.5249
Max Act: 5.2124. Min Act: -0.1700
Data Index: 6471031 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5249. Min Range: -5.5249
Max Act: 5.2124. Min Act: -0.1700
Data Index: 764634 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5249. Min Range: -5.5249
Max Act: 5.1812. Min Act: -0.1700
Data Index: 4568071 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5249. Min Range: -5.5249
Max Act: 5.1499. Min Act: -0.1700
Data Index: 7381500 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5249. Min Range: -5.5249
Max Act: 5.1499. Min Act: -0.1700
Data Index: 1438009 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5249. Min Range: -5.5249
Max Act: 5.1187. Min Act: -0.1700
Data Index: 5802681 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5249. Min Range: -5.5249
Max Act: 5.1499. Min Act: -0.1700
Data Index: 8817334 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5249. Min Range: -5.5249
Max Act: 5.0874. Min Act: -0.1700
Data Index: 8141575 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5249. Min Range: -5.5249
Max Act: 5.0874. Min Act: -0.1700
Data Index: 5185509 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5249. Min Range: -5.5249
Max Act: 5.0874. Min Act: -0.1700
Data Index: 6400938 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5249. Min Range: -5.5249
Max Act: 5.0249. Min Act: -0.1700
Data Index: 3690898 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5249. Min Range: -5.5249
Max Act: 5.0249. Min Act: -0.1700
Data Index: 3711478 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #19