Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3275 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.1846. Min Range: -5.1846
Max Act: 5.1846. Min Act: -0.1700
Data Index: 6621606 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1846. Min Range: -5.1846
Max Act: 5.0596. Min Act: -0.1700
Data Index: 1378621 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1846. Min Range: -5.1846
Max Act: 4.9971. Min Act: -0.1700
Data Index: 1027100 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1846. Min Range: -5.1846
Max Act: 4.9659. Min Act: -0.1700
Data Index: 4561290 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1846. Min Range: -5.1846
Max Act: 4.9659. Min Act: -0.1700
Data Index: 8048381 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1846. Min Range: -5.1846
Max Act: 4.9034. Min Act: -0.1700
Data Index: 1046378 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1846. Min Range: -5.1846
Max Act: 4.9346. Min Act: -0.1700
Data Index: 6820028 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1846. Min Range: -5.1846
Max Act: 4.9346. Min Act: -0.1700
Data Index: 228779 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1846. Min Range: -5.1846
Max Act: 4.9034. Min Act: -0.1700
Data Index: 6756279 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1846. Min Range: -5.1846
Max Act: 4.8721. Min Act: -0.1700
Data Index: 4132660 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1846. Min Range: -5.1846
Max Act: 4.8721. Min Act: -0.1700
Data Index: 6168139 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1846. Min Range: -5.1846
Max Act: 4.8409. Min Act: -0.1700
Data Index: 6536857 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1846. Min Range: -5.1846
Max Act: 4.8721. Min Act: -0.1700
Data Index: 7820012 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1846. Min Range: -5.1846
Max Act: 4.8721. Min Act: -0.1700
Data Index: 5325524 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1846. Min Range: -5.1846
Max Act: 4.8721. Min Act: -0.1700
Data Index: 476472 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1846. Min Range: -5.1846
Max Act: 4.8721. Min Act: -0.1700
Data Index: 7571203 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1846. Min Range: -5.1846
Max Act: 4.8721. Min Act: -0.1700
Data Index: 4749687 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1846. Min Range: -5.1846
Max Act: 4.8721. Min Act: -0.1700
Data Index: 4859284 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1846. Min Range: -5.1846
Max Act: 4.8721. Min Act: -0.1700
Data Index: 292698 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1846. Min Range: -5.1846
Max Act: 4.8409. Min Act: -0.1700
Data Index: 7104817 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #19