Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 806 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.6622. Min Range: -4.6622
Max Act: 4.6622. Min Act: -0.1700
Data Index: 3496838 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6622. Min Range: -4.6622
Max Act: 4.3497. Min Act: -0.1700
Data Index: 3037931 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6622. Min Range: -4.6622
Max Act: 4.3497. Min Act: -0.1700
Data Index: 1065756 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6622. Min Range: -4.6622
Max Act: 4.3497. Min Act: -0.1700
Data Index: 1197953 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6622. Min Range: -4.6622
Max Act: 4.2247. Min Act: -0.1700
Data Index: 4302199 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6622. Min Range: -4.6622
Max Act: 4.2247. Min Act: -0.1700
Data Index: 7014121 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6622. Min Range: -4.6622
Max Act: 4.1934. Min Act: -0.1700
Data Index: 6873938 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6622. Min Range: -4.6622
Max Act: 4.1309. Min Act: -0.1700
Data Index: 6585780 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6622. Min Range: -4.6622
Max Act: 4.1309. Min Act: -0.1700
Data Index: 3677691 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6622. Min Range: -4.6622
Max Act: 4.1309. Min Act: -0.1700
Data Index: 4599189 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6622. Min Range: -4.6622
Max Act: 4.1309. Min Act: -0.1700
Data Index: 3778718 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6622. Min Range: -4.6622
Max Act: 4.0996. Min Act: -0.1700
Data Index: 3578287 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6622. Min Range: -4.6622
Max Act: 4.0996. Min Act: -0.1700
Data Index: 434822 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6622. Min Range: -4.6622
Max Act: 4.0996. Min Act: -0.1700
Data Index: 3578288 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6622. Min Range: -4.6622
Max Act: 4.1309. Min Act: -0.1700
Data Index: 2748578 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6622. Min Range: -4.6622
Max Act: 4.0996. Min Act: -0.1700
Data Index: 3450041 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6622. Min Range: -4.6622
Max Act: 4.0996. Min Act: -0.1700
Data Index: 475488 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6622. Min Range: -4.6622
Max Act: 4.0684. Min Act: -0.1700
Data Index: 287981 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6622. Min Range: -4.6622
Max Act: 4.0059. Min Act: -0.1700
Data Index: 4525890 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6622. Min Range: -4.6622
Max Act: 4.0371. Min Act: -0.1700
Data Index: 2692120 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #19