Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1398 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8430. Min Range: -8.8430
Max Act: 8.8430. Min Act: -0.1700
Data Index: 8438840 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8430. Min Range: -8.8430
Max Act: 8.3430. Min Act: -0.1700
Data Index: 2332596 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8430. Min Range: -8.8430
Max Act: 8.4055. Min Act: -0.1700
Data Index: 7894482 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8430. Min Range: -8.8430
Max Act: 8.3430. Min Act: -0.1700
Data Index: 1297102 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8430. Min Range: -8.8430
Max Act: 8.2805. Min Act: -0.1700
Data Index: 3585004 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8430. Min Range: -8.8430
Max Act: 8.2180. Min Act: -0.1700
Data Index: 8261012 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8430. Min Range: -8.8430
Max Act: 8.2180. Min Act: -0.1700
Data Index: 6703436 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8430. Min Range: -8.8430
Max Act: 8.2180. Min Act: -0.1700
Data Index: 8761286 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8430. Min Range: -8.8430
Max Act: 8.2180. Min Act: -0.1700
Data Index: 7846326 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8430. Min Range: -8.8430
Max Act: 8.0305. Min Act: -0.1700
Data Index: 4863362 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8430. Min Range: -8.8430
Max Act: 8.0930. Min Act: -0.1700
Data Index: 7683362 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8430. Min Range: -8.8430
Max Act: 8.0305. Min Act: -0.1700
Data Index: 7756769 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8430. Min Range: -8.8430
Max Act: 7.9680. Min Act: -0.1700
Data Index: 227542 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8430. Min Range: -8.8430
Max Act: 8.0305. Min Act: -0.1700
Data Index: 6876379 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8430. Min Range: -8.8430
Max Act: 7.9680. Min Act: -0.1700
Data Index: 2612197 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8430. Min Range: -8.8430
Max Act: 7.9055. Min Act: -0.1700
Data Index: 2659044 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8430. Min Range: -8.8430
Max Act: 7.9055. Min Act: -0.1700
Data Index: 7891992 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8430. Min Range: -8.8430
Max Act: 7.9055. Min Act: -0.1700
Data Index: 1540694 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8430. Min Range: -8.8430
Max Act: 7.9055. Min Act: -0.1700
Data Index: 1927151 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8430. Min Range: -8.8430
Max Act: 7.9055. Min Act: -0.1700
Data Index: 2888134 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #19