Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6396 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4311. Min Range: -4.4311
Max Act: 4.4311. Min Act: -0.1700
Data Index: 4851936 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4311. Min Range: -4.4311
Max Act: 4.3374. Min Act: -0.1700
Data Index: 1798018 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4311. Min Range: -4.4311
Max Act: 4.3374. Min Act: -0.1700
Data Index: 4164420 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4311. Min Range: -4.4311
Max Act: 4.3686. Min Act: -0.1700
Data Index: 83642 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4311. Min Range: -4.4311
Max Act: 4.3061. Min Act: -0.1700
Data Index: 7497864 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4311. Min Range: -4.4311
Max Act: 4.3061. Min Act: -0.1700
Data Index: 7497863 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4311. Min Range: -4.4311
Max Act: 4.2436. Min Act: -0.1700
Data Index: 994640 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4311. Min Range: -4.4311
Max Act: 4.1811. Min Act: -0.1700
Data Index: 1394467 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4311. Min Range: -4.4311
Max Act: 4.1811. Min Act: -0.1700
Data Index: 6744238 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4311. Min Range: -4.4311
Max Act: 4.1499. Min Act: -0.1700
Data Index: 8003387 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4311. Min Range: -4.4311
Max Act: 4.1499. Min Act: -0.1700
Data Index: 4062666 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4311. Min Range: -4.4311
Max Act: 4.1186. Min Act: -0.1700
Data Index: 3855297 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4311. Min Range: -4.4311
Max Act: 4.0561. Min Act: -0.1700
Data Index: 4404408 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4311. Min Range: -4.4311
Max Act: 4.0561. Min Act: -0.1700
Data Index: 2348914 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4311. Min Range: -4.4311
Max Act: 4.0561. Min Act: -0.1700
Data Index: 3325778 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4311. Min Range: -4.4311
Max Act: 4.0248. Min Act: -0.1700
Data Index: 2367548 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4311. Min Range: -4.4311
Max Act: 4.0248. Min Act: -0.1700
Data Index: 939175 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4311. Min Range: -4.4311
Max Act: 4.0248. Min Act: -0.1700
Data Index: 7896869 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4311. Min Range: -4.4311
Max Act: 4.0248. Min Act: -0.1700
Data Index: 5662435 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4311. Min Range: -4.4311
Max Act: 3.9936. Min Act: -0.1700
Data Index: 7896868 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #19