Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3553 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3773. Min Range: -8.3773
Max Act: 8.3773. Min Act: -0.1700
Data Index: 8060069 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3773. Min Range: -8.3773
Max Act: 8.3148. Min Act: -0.1700
Data Index: 5765416 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3773. Min Range: -8.3773
Max Act: 8.1898. Min Act: -0.1700
Data Index: 1406352 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3773. Min Range: -8.3773
Max Act: 7.9398. Min Act: -0.1700
Data Index: 7807547 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3773. Min Range: -8.3773
Max Act: 7.8773. Min Act: -0.1700
Data Index: 8019029 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3773. Min Range: -8.3773
Max Act: 7.8460. Min Act: -0.1700
Data Index: 2461563 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3773. Min Range: -8.3773
Max Act: 7.8460. Min Act: -0.1700
Data Index: 3701388 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3773. Min Range: -8.3773
Max Act: 7.8460. Min Act: -0.1700
Data Index: 763133 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3773. Min Range: -8.3773
Max Act: 7.8148. Min Act: -0.1700
Data Index: 6444092 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3773. Min Range: -8.3773
Max Act: 7.7835. Min Act: -0.1700
Data Index: 2491215 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3773. Min Range: -8.3773
Max Act: 7.7210. Min Act: -0.1700
Data Index: 1633498 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3773. Min Range: -8.3773
Max Act: 7.7210. Min Act: -0.1700
Data Index: 3094645 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3773. Min Range: -8.3773
Max Act: 7.7210. Min Act: -0.1700
Data Index: 166496 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3773. Min Range: -8.3773
Max Act: 7.6898. Min Act: -0.1700
Data Index: 8302560 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3773. Min Range: -8.3773
Max Act: 7.6898. Min Act: -0.1700
Data Index: 3434912 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3773. Min Range: -8.3773
Max Act: 7.6585. Min Act: -0.1700
Data Index: 1894543 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3773. Min Range: -8.3773
Max Act: 7.6898. Min Act: -0.1700
Data Index: 5303245 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3773. Min Range: -8.3773
Max Act: 7.6898. Min Act: -0.1700
Data Index: 6415137 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3773. Min Range: -8.3773
Max Act: 7.6585. Min Act: -0.1700
Data Index: 6628027 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3773. Min Range: -8.3773
Max Act: 7.6273. Min Act: -0.1700
Data Index: 4872497 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #19