Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2704 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.8910. Min Range: -3.8910
Max Act: 3.8910. Min Act: -0.1700
Data Index: 5652509 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8910. Min Range: -3.8910
Max Act: 3.7503. Min Act: -0.1700
Data Index: 2547001 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8910. Min Range: -3.8910
Max Act: 3.7034. Min Act: -0.1700
Data Index: 5095585 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8910. Min Range: -3.8910
Max Act: 3.6564. Min Act: -0.1700
Data Index: 24845 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8910. Min Range: -3.8910
Max Act: 3.6721. Min Act: -0.1700
Data Index: 3685062 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8910. Min Range: -3.8910
Max Act: 3.6408. Min Act: -0.1700
Data Index: 189477 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8910. Min Range: -3.8910
Max Act: 3.6564. Min Act: -0.1700
Data Index: 7310226 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8910. Min Range: -3.8910
Max Act: 3.6095. Min Act: -0.1700
Data Index: 7605696 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8910. Min Range: -3.8910
Max Act: 3.5938. Min Act: -0.1700
Data Index: 2582708 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8910. Min Range: -3.8910
Max Act: 3.5782. Min Act: -0.1700
Data Index: 266704 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8910. Min Range: -3.8910
Max Act: 3.5625. Min Act: -0.1700
Data Index: 5537638 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8910. Min Range: -3.8910
Max Act: 3.5782. Min Act: -0.1700
Data Index: 6063704 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8910. Min Range: -3.8910
Max Act: 3.5469. Min Act: -0.1700
Data Index: 8584576 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8910. Min Range: -3.8910
Max Act: 3.4842. Min Act: -0.1700
Data Index: 3481587 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8910. Min Range: -3.8910
Max Act: 3.5312. Min Act: -0.1700
Data Index: 2244786 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8910. Min Range: -3.8910
Max Act: 3.4842. Min Act: -0.1700
Data Index: 1113491 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8910. Min Range: -3.8910
Max Act: 3.4999. Min Act: -0.1700
Data Index: 3278827 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8910. Min Range: -3.8910
Max Act: 3.4529. Min Act: -0.1700
Data Index: 5717647 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8910. Min Range: -3.8910
Max Act: 3.4686. Min Act: -0.1700
Data Index: 4478420 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8910. Min Range: -3.8910
Max Act: 3.4372. Min Act: -0.1700
Data Index: 6496400 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #19