Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 436 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.3516. Min Range: -5.3516
Max Act: 5.3516. Min Act: -0.1700
Data Index: 7790299 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3516. Min Range: -5.3516
Max Act: 5.3203. Min Act: -0.1700
Data Index: 80837 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3516. Min Range: -5.3516
Max Act: 5.2891. Min Act: -0.1700
Data Index: 3330703 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3516. Min Range: -5.3516
Max Act: 5.2578. Min Act: -0.1700
Data Index: 5652009 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3516. Min Range: -5.3516
Max Act: 5.2266. Min Act: -0.1700
Data Index: 2170805 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3516. Min Range: -5.3516
Max Act: 5.2266. Min Act: -0.1700
Data Index: 4330516 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3516. Min Range: -5.3516
Max Act: 5.1641. Min Act: -0.1700
Data Index: 3770306 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3516. Min Range: -5.3516
Max Act: 5.1016. Min Act: -0.1700
Data Index: 759019 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3516. Min Range: -5.3516
Max Act: 5.1016. Min Act: -0.1700
Data Index: 6093589 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3516. Min Range: -5.3516
Max Act: 5.1328. Min Act: -0.1700
Data Index: 3454983 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3516. Min Range: -5.3516
Max Act: 5.1016. Min Act: -0.1700
Data Index: 8750863 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3516. Min Range: -5.3516
Max Act: 5.1328. Min Act: -0.1700
Data Index: 2264713 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3516. Min Range: -5.3516
Max Act: 5.1016. Min Act: -0.1700
Data Index: 5321834 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3516. Min Range: -5.3516
Max Act: 5.1016. Min Act: -0.1700
Data Index: 8800349 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3516. Min Range: -5.3516
Max Act: 5.1016. Min Act: -0.1700
Data Index: 5065643 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3516. Min Range: -5.3516
Max Act: 5.0703. Min Act: -0.1700
Data Index: 7396156 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3516. Min Range: -5.3516
Max Act: 5.1016. Min Act: -0.1700
Data Index: 4595587 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3516. Min Range: -5.3516
Max Act: 5.0703. Min Act: -0.1700
Data Index: 6298665 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3516. Min Range: -5.3516
Max Act: 5.0078. Min Act: -0.1700
Data Index: 3748759 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3516. Min Range: -5.3516
Max Act: 5.0078. Min Act: -0.1700
Data Index: 6385743 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #19