Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 225 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0622. Min Range: -9.0622
Max Act: 9.0622. Min Act: -0.1700
Data Index: 6120682 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0622. Min Range: -9.0622
Max Act: 8.9372. Min Act: -0.1700
Data Index: 3636655 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0622. Min Range: -9.0622
Max Act: 8.9372. Min Act: -0.1700
Data Index: 1933490 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0622. Min Range: -9.0622
Max Act: 8.8747. Min Act: -0.1700
Data Index: 8443573 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0622. Min Range: -9.0622
Max Act: 8.8122. Min Act: -0.1700
Data Index: 5751634 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0622. Min Range: -9.0622
Max Act: 8.7497. Min Act: -0.1700
Data Index: 1661178 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0622. Min Range: -9.0622
Max Act: 8.6872. Min Act: -0.1700
Data Index: 3003545 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0622. Min Range: -9.0622
Max Act: 8.6247. Min Act: -0.1700
Data Index: 372553 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0622. Min Range: -9.0622
Max Act: 8.6872. Min Act: -0.1700
Data Index: 1786481 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0622. Min Range: -9.0622
Max Act: 8.6247. Min Act: -0.1700
Data Index: 5605227 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0622. Min Range: -9.0622
Max Act: 8.4372. Min Act: -0.1700
Data Index: 7249610 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0622. Min Range: -9.0622
Max Act: 8.4997. Min Act: -0.1700
Data Index: 7628897 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0622. Min Range: -9.0622
Max Act: 8.4372. Min Act: -0.1700
Data Index: 5988438 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0622. Min Range: -9.0622
Max Act: 8.4372. Min Act: -0.1700
Data Index: 4352753 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0622. Min Range: -9.0622
Max Act: 8.4372. Min Act: -0.1700
Data Index: 1986816 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0622. Min Range: -9.0622
Max Act: 8.4372. Min Act: -0.1700
Data Index: 6972672 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0622. Min Range: -9.0622
Max Act: 8.3747. Min Act: -0.1700
Data Index: 1928486 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0622. Min Range: -9.0622
Max Act: 8.3747. Min Act: -0.1700
Data Index: 6676087 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0622. Min Range: -9.0622
Max Act: 8.3747. Min Act: -0.1700
Data Index: 2047720 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0622. Min Range: -9.0622
Max Act: 8.3122. Min Act: -0.1700
Data Index: 7143381 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #19