Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3206 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.1853. Min Range: -5.1853
Max Act: 5.1853. Min Act: -0.1700
Data Index: 8639987 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1853. Min Range: -5.1853
Max Act: 5.0603. Min Act: -0.1700
Data Index: 8639988 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1853. Min Range: -5.1853
Max Act: 4.9978. Min Act: -0.1700
Data Index: 2738805 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1853. Min Range: -5.1853
Max Act: 4.9353. Min Act: -0.1700
Data Index: 8166074 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1853. Min Range: -5.1853
Max Act: 4.9353. Min Act: -0.1700
Data Index: 5982550 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1853. Min Range: -5.1853
Max Act: 4.9353. Min Act: -0.1700
Data Index: 5281010 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1853. Min Range: -5.1853
Max Act: 4.9041. Min Act: -0.1700
Data Index: 3959709 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1853. Min Range: -5.1853
Max Act: 4.9353. Min Act: -0.1700
Data Index: 1393167 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1853. Min Range: -5.1853
Max Act: 4.9353. Min Act: -0.1700
Data Index: 3019170 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1853. Min Range: -5.1853
Max Act: 4.9353. Min Act: -0.1700
Data Index: 2861303 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1853. Min Range: -5.1853
Max Act: 4.9353. Min Act: -0.1700
Data Index: 3553384 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1853. Min Range: -5.1853
Max Act: 4.9041. Min Act: -0.1700
Data Index: 4436793 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1853. Min Range: -5.1853
Max Act: 4.9353. Min Act: -0.1700
Data Index: 11089 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1853. Min Range: -5.1853
Max Act: 4.9041. Min Act: -0.1700
Data Index: 5718039 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1853. Min Range: -5.1853
Max Act: 4.9041. Min Act: -0.1700
Data Index: 604188 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1853. Min Range: -5.1853
Max Act: 4.9041. Min Act: -0.1700
Data Index: 196005 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1853. Min Range: -5.1853
Max Act: 4.9041. Min Act: -0.1700
Data Index: 6512743 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1853. Min Range: -5.1853
Max Act: 4.9041. Min Act: -0.1700
Data Index: 7183871 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1853. Min Range: -5.1853
Max Act: 4.9041. Min Act: -0.1700
Data Index: 7488570 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1853. Min Range: -5.1853
Max Act: 4.9041. Min Act: -0.1700
Data Index: 7518391 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #19