Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4113 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8081. Min Range: -8.8081
Max Act: 8.8081. Min Act: -0.1700
Data Index: 8640936 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8081. Min Range: -8.8081
Max Act: 8.2456. Min Act: -0.1700
Data Index: 5274815 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8081. Min Range: -8.8081
Max Act: 8.1831. Min Act: -0.1700
Data Index: 6526414 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8081. Min Range: -8.8081
Max Act: 8.1206. Min Act: -0.1700
Data Index: 6124438 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8081. Min Range: -8.8081
Max Act: 8.1206. Min Act: -0.1700
Data Index: 4893160 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8081. Min Range: -8.8081
Max Act: 8.0581. Min Act: -0.1700
Data Index: 3645357 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8081. Min Range: -8.8081
Max Act: 8.0581. Min Act: -0.1700
Data Index: 6240453 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8081. Min Range: -8.8081
Max Act: 8.0581. Min Act: -0.1700
Data Index: 651141 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8081. Min Range: -8.8081
Max Act: 7.9956. Min Act: -0.1700
Data Index: 3104892 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8081. Min Range: -8.8081
Max Act: 7.9956. Min Act: -0.1700
Data Index: 2276492 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8081. Min Range: -8.8081
Max Act: 7.9956. Min Act: -0.1700
Data Index: 1884537 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8081. Min Range: -8.8081
Max Act: 7.9331. Min Act: -0.1700
Data Index: 2278435 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8081. Min Range: -8.8081
Max Act: 7.9019. Min Act: -0.1700
Data Index: 2274463 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8081. Min Range: -8.8081
Max Act: 7.9331. Min Act: -0.1700
Data Index: 5416424 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8081. Min Range: -8.8081
Max Act: 7.8706. Min Act: -0.1700
Data Index: 3761364 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8081. Min Range: -8.8081
Max Act: 7.8706. Min Act: -0.1700
Data Index: 6017860 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8081. Min Range: -8.8081
Max Act: 7.8394. Min Act: -0.1700
Data Index: 7845489 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8081. Min Range: -8.8081
Max Act: 7.8394. Min Act: -0.1700
Data Index: 8302738 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8081. Min Range: -8.8081
Max Act: 7.8081. Min Act: -0.1700
Data Index: 3651711 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8081. Min Range: -8.8081
Max Act: 7.8081. Min Act: -0.1700
Data Index: 1924503 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #19