Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 370 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9775. Min Range: -7.9775
Max Act: 7.9775. Min Act: -0.1700
Data Index: 5154848 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9775. Min Range: -7.9775
Max Act: 7.9150. Min Act: -0.1700
Data Index: 5031286 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9775. Min Range: -7.9775
Max Act: 7.9150. Min Act: -0.1700
Data Index: 6023472 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9775. Min Range: -7.9775
Max Act: 7.9150. Min Act: -0.1700
Data Index: 7517081 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9775. Min Range: -7.9775
Max Act: 7.7275. Min Act: -0.1700
Data Index: 2885727 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9775. Min Range: -7.9775
Max Act: 7.7900. Min Act: -0.1700
Data Index: 2899211 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9775. Min Range: -7.9775
Max Act: 7.7900. Min Act: -0.1700
Data Index: 8223359 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9775. Min Range: -7.9775
Max Act: 7.7900. Min Act: -0.1700
Data Index: 1971653 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9775. Min Range: -7.9775
Max Act: 7.7275. Min Act: -0.1700
Data Index: 5917109 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9775. Min Range: -7.9775
Max Act: 7.6650. Min Act: -0.1700
Data Index: 4565324 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9775. Min Range: -7.9775
Max Act: 7.6650. Min Act: -0.1700
Data Index: 5248844 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9775. Min Range: -7.9775
Max Act: 7.6025. Min Act: -0.1700
Data Index: 3827663 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9775. Min Range: -7.9775
Max Act: 7.6337. Min Act: -0.1700
Data Index: 3548378 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9775. Min Range: -7.9775
Max Act: 7.6337. Min Act: -0.1700
Data Index: 803215 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9775. Min Range: -7.9775
Max Act: 7.6025. Min Act: -0.1700
Data Index: 1219440 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9775. Min Range: -7.9775
Max Act: 7.6025. Min Act: -0.1700
Data Index: 7880910 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9775. Min Range: -7.9775
Max Act: 7.6025. Min Act: -0.1700
Data Index: 3471018 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9775. Min Range: -7.9775
Max Act: 7.5712. Min Act: -0.1700
Data Index: 8381030 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9775. Min Range: -7.9775
Max Act: 7.5400. Min Act: -0.1700
Data Index: 2968206 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9775. Min Range: -7.9775
Max Act: 7.5400. Min Act: -0.1700
Data Index: 6305277 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #19