Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1521 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.9641. Min Range: -3.9641
Max Act: 3.9641. Min Act: -0.1700
Data Index: 6906266 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9641. Min Range: -3.9641
Max Act: 3.9015. Min Act: -0.1700
Data Index: 3426714 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9641. Min Range: -3.9641
Max Act: 3.9015. Min Act: -0.1700
Data Index: 1647466 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9641. Min Range: -3.9641
Max Act: 3.9015. Min Act: -0.1700
Data Index: 55412 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9641. Min Range: -3.9641
Max Act: 3.8703. Min Act: -0.1700
Data Index: 4609428 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9641. Min Range: -3.9641
Max Act: 3.8703. Min Act: -0.1700
Data Index: 8017508 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9641. Min Range: -3.9641
Max Act: 3.8390. Min Act: -0.1700
Data Index: 3537240 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9641. Min Range: -3.9641
Max Act: 3.8390. Min Act: -0.1700
Data Index: 3346870 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9641. Min Range: -3.9641
Max Act: 3.8234. Min Act: -0.1700
Data Index: 312556 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9641. Min Range: -3.9641
Max Act: 3.8234. Min Act: -0.1700
Data Index: 6882341 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9641. Min Range: -3.9641
Max Act: 3.8077. Min Act: -0.1700
Data Index: 4903293 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9641. Min Range: -3.9641
Max Act: 3.8077. Min Act: -0.1700
Data Index: 5040045 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9641. Min Range: -3.9641
Max Act: 3.7452. Min Act: -0.1700
Data Index: 2815018 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9641. Min Range: -3.9641
Max Act: 3.7921. Min Act: -0.1700
Data Index: 3564586 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9641. Min Range: -3.9641
Max Act: 3.8077. Min Act: -0.1700
Data Index: 7707839 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9641. Min Range: -3.9641
Max Act: 3.8077. Min Act: -0.1700
Data Index: 8813846 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9641. Min Range: -3.9641
Max Act: 3.7608. Min Act: -0.1700
Data Index: 7115857 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9641. Min Range: -3.9641
Max Act: 3.7608. Min Act: -0.1700
Data Index: 2738431 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9641. Min Range: -3.9641
Max Act: 3.7765. Min Act: -0.1700
Data Index: 8737263 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9641. Min Range: -3.9641
Max Act: 3.7608. Min Act: -0.1700
Data Index: 5428509 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #19