Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 843 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8314. Min Range: -5.8314
Max Act: 5.8314. Min Act: -0.1700
Data Index: 1368774 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8314. Min Range: -5.8314
Max Act: 5.8001. Min Act: -0.1700
Data Index: 1368775 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8314. Min Range: -5.8314
Max Act: 5.1439. Min Act: -0.1700
Data Index: 6261700 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8314. Min Range: -5.8314
Max Act: 5.0814. Min Act: -0.1700
Data Index: 2902379 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8314. Min Range: -5.8314
Max Act: 4.9876. Min Act: -0.1700
Data Index: 2190233 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8314. Min Range: -5.8314
Max Act: 4.9564. Min Act: -0.1700
Data Index: 6151537 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8314. Min Range: -5.8314
Max Act: 4.9251. Min Act: -0.1700
Data Index: 1093194 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8314. Min Range: -5.8314
Max Act: 4.8939. Min Act: -0.1700
Data Index: 4192954 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8314. Min Range: -5.8314
Max Act: 4.8939. Min Act: -0.1700
Data Index: 981441 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8314. Min Range: -5.8314
Max Act: 4.8626. Min Act: -0.1700
Data Index: 256205 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8314. Min Range: -5.8314
Max Act: 4.8314. Min Act: -0.1700
Data Index: 672488 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8314. Min Range: -5.8314
Max Act: 4.8001. Min Act: -0.1700
Data Index: 5119424 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8314. Min Range: -5.8314
Max Act: 4.8001. Min Act: -0.1700
Data Index: 1272514 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8314. Min Range: -5.8314
Max Act: 4.7689. Min Act: -0.1700
Data Index: 8277920 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8314. Min Range: -5.8314
Max Act: 4.7689. Min Act: -0.1700
Data Index: 7497962 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8314. Min Range: -5.8314
Max Act: 4.7376. Min Act: -0.1700
Data Index: 6362868 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8314. Min Range: -5.8314
Max Act: 4.7064. Min Act: -0.1700
Data Index: 8223597 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8314. Min Range: -5.8314
Max Act: 4.7064. Min Act: -0.1700
Data Index: 3428487 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8314. Min Range: -5.8314
Max Act: 4.6751. Min Act: -0.1700
Data Index: 6610668 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8314. Min Range: -5.8314
Max Act: 4.6751. Min Act: -0.1700
Data Index: 7291789 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #19