Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4932 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2114. Min Range: -5.2114
Max Act: 5.2114. Min Act: -0.1700
Data Index: 3342329 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2114. Min Range: -5.2114
Max Act: 5.1177. Min Act: -0.1700
Data Index: 6151814 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2114. Min Range: -5.2114
Max Act: 5.0864. Min Act: -0.1700
Data Index: 8626068 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2114. Min Range: -5.2114
Max Act: 5.0552. Min Act: -0.1700
Data Index: 4583271 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2114. Min Range: -5.2114
Max Act: 5.0552. Min Act: -0.1700
Data Index: 3765674 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2114. Min Range: -5.2114
Max Act: 5.0552. Min Act: -0.1700
Data Index: 5509650 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2114. Min Range: -5.2114
Max Act: 5.0239. Min Act: -0.1700
Data Index: 7629629 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2114. Min Range: -5.2114
Max Act: 5.0552. Min Act: -0.1700
Data Index: 7423918 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2114. Min Range: -5.2114
Max Act: 5.0239. Min Act: -0.1700
Data Index: 3747271 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2114. Min Range: -5.2114
Max Act: 5.0239. Min Act: -0.1700
Data Index: 4486715 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2114. Min Range: -5.2114
Max Act: 4.9927. Min Act: -0.1700
Data Index: 2230212 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2114. Min Range: -5.2114
Max Act: 5.0239. Min Act: -0.1700
Data Index: 6861909 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2114. Min Range: -5.2114
Max Act: 4.9927. Min Act: -0.1700
Data Index: 4226004 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2114. Min Range: -5.2114
Max Act: 5.0239. Min Act: -0.1700
Data Index: 5696837 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2114. Min Range: -5.2114
Max Act: 4.9927. Min Act: -0.1700
Data Index: 8373051 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2114. Min Range: -5.2114
Max Act: 4.9614. Min Act: -0.1700
Data Index: 1072584 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2114. Min Range: -5.2114
Max Act: 4.9614. Min Act: -0.1700
Data Index: 1895678 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2114. Min Range: -5.2114
Max Act: 4.9614. Min Act: -0.1700
Data Index: 4036192 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2114. Min Range: -5.2114
Max Act: 4.9614. Min Act: -0.1700
Data Index: 7085080 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2114. Min Range: -5.2114
Max Act: 4.9614. Min Act: -0.1700
Data Index: 6293121 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #19