Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6334 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8754. Min Range: -8.8754
Max Act: 8.8754. Min Act: -0.1700
Data Index: 2313977 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8754. Min Range: -8.8754
Max Act: 8.5629. Min Act: -0.1700
Data Index: 2753064 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8754. Min Range: -8.8754
Max Act: 8.5004. Min Act: -0.1698
Data Index: 2156925 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8754. Min Range: -8.8754
Max Act: 8.3129. Min Act: -0.1700
Data Index: 297443 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8754. Min Range: -8.8754
Max Act: 8.3129. Min Act: -0.1700
Data Index: 5790357 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8754. Min Range: -8.8754
Max Act: 8.2504. Min Act: -0.1700
Data Index: 7886171 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8754. Min Range: -8.8754
Max Act: 8.3129. Min Act: -0.1700
Data Index: 3469786 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8754. Min Range: -8.8754
Max Act: 8.2504. Min Act: -0.1700
Data Index: 3730665 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8754. Min Range: -8.8754
Max Act: 8.2504. Min Act: -0.1700
Data Index: 8702972 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8754. Min Range: -8.8754
Max Act: 8.1879. Min Act: -0.1700
Data Index: 4466166 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8754. Min Range: -8.8754
Max Act: 8.1254. Min Act: -0.1698
Data Index: 5975139 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8754. Min Range: -8.8754
Max Act: 8.1254. Min Act: -0.1698
Data Index: 939033 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8754. Min Range: -8.8754
Max Act: 8.1254. Min Act: -0.1700
Data Index: 6611776 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8754. Min Range: -8.8754
Max Act: 8.1254. Min Act: -0.1700
Data Index: 1305092 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8754. Min Range: -8.8754
Max Act: 8.0629. Min Act: -0.1700
Data Index: 5073062 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8754. Min Range: -8.8754
Max Act: 8.0629. Min Act: -0.1700
Data Index: 5065962 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8754. Min Range: -8.8754
Max Act: 8.0004. Min Act: -0.1700
Data Index: 1006931 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8754. Min Range: -8.8754
Max Act: 8.0004. Min Act: -0.1700
Data Index: 4984679 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8754. Min Range: -8.8754
Max Act: 7.9379. Min Act: -0.1700
Data Index: 4539057 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8754. Min Range: -8.8754
Max Act: 7.9379. Min Act: -0.1700
Data Index: 4002314 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #19