Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2982 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 12.2760. Min Range: -12.2760
Max Act: 12.2760. Min Act: -0.1700
Data Index: 5885276 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.2760. Min Range: -12.2760
Max Act: 11.7135. Min Act: -0.1700
Data Index: 2756750 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.2760. Min Range: -12.2760
Max Act: 11.2135. Min Act: -0.1700
Data Index: 559679 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.2760. Min Range: -12.2760
Max Act: 10.4010. Min Act: -0.1700
Data Index: 1088107 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.2760. Min Range: -12.2760
Max Act: 10.2135. Min Act: -0.1700
Data Index: 5362738 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.2760. Min Range: -12.2760
Max Act: 10.2135. Min Act: -0.1700
Data Index: 4798426 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.2760. Min Range: -12.2760
Max Act: 10.1510. Min Act: -0.1700
Data Index: 4798421 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.2760. Min Range: -12.2760
Max Act: 10.0885. Min Act: -0.1700
Data Index: 7845198 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.2760. Min Range: -12.2760
Max Act: 10.0260. Min Act: -0.1700
Data Index: 4250798 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.2760. Min Range: -12.2760
Max Act: 9.9635. Min Act: -0.1700
Data Index: 2103098 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.2760. Min Range: -12.2760
Max Act: 9.9010. Min Act: -0.1700
Data Index: 35659 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.2760. Min Range: -12.2760
Max Act: 9.9010. Min Act: -0.1700
Data Index: 5038425 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.2760. Min Range: -12.2760
Max Act: 9.9635. Min Act: -0.1700
Data Index: 7592037 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.2760. Min Range: -12.2760
Max Act: 9.9010. Min Act: -0.1700
Data Index: 2174738 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.2760. Min Range: -12.2760
Max Act: 9.9635. Min Act: -0.1700
Data Index: 6431042 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.2760. Min Range: -12.2760
Max Act: 9.9010. Min Act: -0.1700
Data Index: 1090020 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.2760. Min Range: -12.2760
Max Act: 9.9010. Min Act: -0.1700
Data Index: 2103087 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.2760. Min Range: -12.2760
Max Act: 9.8385. Min Act: -0.1700
Data Index: 1090027 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.2760. Min Range: -12.2760
Max Act: 9.8385. Min Act: -0.1700
Data Index: 4085023 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.2760. Min Range: -12.2760
Max Act: 9.7760. Min Act: -0.1700
Data Index: 1811777 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #19