Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3224 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3087. Min Range: -6.3087
Max Act: 6.3087. Min Act: -0.1700
Data Index: 118474 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3087. Min Range: -6.3087
Max Act: 6.2149. Min Act: -0.1700
Data Index: 7871429 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3087. Min Range: -6.3087
Max Act: 6.2149. Min Act: -0.1700
Data Index: 3765487 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3087. Min Range: -6.3087
Max Act: 6.1837. Min Act: -0.1700
Data Index: 2118074 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3087. Min Range: -6.3087
Max Act: 6.1837. Min Act: -0.1700
Data Index: 5414622 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3087. Min Range: -6.3087
Max Act: 6.1212. Min Act: -0.1700
Data Index: 2716533 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3087. Min Range: -6.3087
Max Act: 6.1212. Min Act: -0.1700
Data Index: 2905290 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3087. Min Range: -6.3087
Max Act: 6.1212. Min Act: -0.1700
Data Index: 1436225 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3087. Min Range: -6.3087
Max Act: 6.1212. Min Act: -0.1700
Data Index: 8502726 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3087. Min Range: -6.3087
Max Act: 6.0899. Min Act: -0.1700
Data Index: 1297637 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3087. Min Range: -6.3087
Max Act: 6.0899. Min Act: -0.1700
Data Index: 1177866 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3087. Min Range: -6.3087
Max Act: 6.0899. Min Act: -0.1700
Data Index: 5265849 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3087. Min Range: -6.3087
Max Act: 6.0899. Min Act: -0.1700
Data Index: 8775963 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3087. Min Range: -6.3087
Max Act: 6.0587. Min Act: -0.1700
Data Index: 1570410 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3087. Min Range: -6.3087
Max Act: 6.0587. Min Act: -0.1700
Data Index: 5301908 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3087. Min Range: -6.3087
Max Act: 6.0587. Min Act: -0.1700
Data Index: 6379703 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3087. Min Range: -6.3087
Max Act: 6.0274. Min Act: -0.1700
Data Index: 2375230 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3087. Min Range: -6.3087
Max Act: 5.9962. Min Act: -0.1700
Data Index: 2001016 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3087. Min Range: -6.3087
Max Act: 5.9649. Min Act: -0.1700
Data Index: 6284808 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3087. Min Range: -6.3087
Max Act: 5.9962. Min Act: -0.1700
Data Index: 1162709 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #19