Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 19 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6982. Min Range: -7.6982
Max Act: 7.6982. Min Act: -0.1700
Data Index: 5998237 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6982. Min Range: -7.6982
Max Act: 7.6669. Min Act: -0.1700
Data Index: 3739155 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6982. Min Range: -7.6982
Max Act: 7.6044. Min Act: -0.1700
Data Index: 1176622 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6982. Min Range: -7.6982
Max Act: 7.5732. Min Act: -0.1700
Data Index: 533606 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6982. Min Range: -7.6982
Max Act: 7.5732. Min Act: -0.1700
Data Index: 3488293 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6982. Min Range: -7.6982
Max Act: 7.5732. Min Act: -0.1700
Data Index: 2643758 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6982. Min Range: -7.6982
Max Act: 7.5732. Min Act: -0.1700
Data Index: 2246805 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6982. Min Range: -7.6982
Max Act: 7.5419. Min Act: -0.1700
Data Index: 3872897 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6982. Min Range: -7.6982
Max Act: 7.5419. Min Act: -0.1700
Data Index: 5579284 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6982. Min Range: -7.6982
Max Act: 7.5107. Min Act: -0.1700
Data Index: 478814 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6982. Min Range: -7.6982
Max Act: 7.4482. Min Act: -0.1700
Data Index: 3434674 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6982. Min Range: -7.6982
Max Act: 7.4794. Min Act: -0.1700
Data Index: 483569 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6982. Min Range: -7.6982
Max Act: 7.4482. Min Act: -0.1700
Data Index: 483567 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6982. Min Range: -7.6982
Max Act: 7.4482. Min Act: -0.1700
Data Index: 5249028 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6982. Min Range: -7.6982
Max Act: 7.3857. Min Act: -0.1700
Data Index: 192614 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6982. Min Range: -7.6982
Max Act: 7.4169. Min Act: -0.1700
Data Index: 7136111 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6982. Min Range: -7.6982
Max Act: 7.4169. Min Act: -0.1700
Data Index: 483568 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6982. Min Range: -7.6982
Max Act: 7.3544. Min Act: -0.1700
Data Index: 7978215 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6982. Min Range: -7.6982
Max Act: 7.3544. Min Act: -0.1700
Data Index: 2453724 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6982. Min Range: -7.6982
Max Act: 7.3544. Min Act: -0.1700
Data Index: 5998236 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #19