Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3913 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8407. Min Range: -5.8407
Max Act: 5.8407. Min Act: -0.1700
Data Index: 4164890 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8407. Min Range: -5.8407
Max Act: 5.8094. Min Act: -0.1700
Data Index: 8717562 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8407. Min Range: -5.8407
Max Act: 5.7782. Min Act: -0.1700
Data Index: 2728778 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8407. Min Range: -5.8407
Max Act: 5.7157. Min Act: -0.1700
Data Index: 7385841 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8407. Min Range: -5.8407
Max Act: 5.7157. Min Act: -0.1700
Data Index: 2118422 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8407. Min Range: -5.8407
Max Act: 5.7469. Min Act: -0.1700
Data Index: 8567704 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8407. Min Range: -5.8407
Max Act: 5.6844. Min Act: -0.1700
Data Index: 5204200 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8407. Min Range: -5.8407
Max Act: 5.6532. Min Act: -0.1700
Data Index: 7123015 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8407. Min Range: -5.8407
Max Act: 5.6532. Min Act: -0.1700
Data Index: 1251308 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8407. Min Range: -5.8407
Max Act: 5.6532. Min Act: -0.1700
Data Index: 7245253 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8407. Min Range: -5.8407
Max Act: 5.6532. Min Act: -0.1700
Data Index: 5174325 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8407. Min Range: -5.8407
Max Act: 5.6219. Min Act: -0.1700
Data Index: 4854954 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8407. Min Range: -5.8407
Max Act: 5.5907. Min Act: -0.1700
Data Index: 5151252 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8407. Min Range: -5.8407
Max Act: 5.5907. Min Act: -0.1700
Data Index: 5775807 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8407. Min Range: -5.8407
Max Act: 5.5907. Min Act: -0.1700
Data Index: 2888035 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8407. Min Range: -5.8407
Max Act: 5.5907. Min Act: -0.1700
Data Index: 2750394 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8407. Min Range: -5.8407
Max Act: 5.5907. Min Act: -0.1700
Data Index: 2639131 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8407. Min Range: -5.8407
Max Act: 5.5594. Min Act: -0.1700
Data Index: 4444561 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8407. Min Range: -5.8407
Max Act: 5.5594. Min Act: -0.1700
Data Index: 7792618 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8407. Min Range: -5.8407
Max Act: 5.4969. Min Act: -0.1700
Data Index: 6849979 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #19