Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1824 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.1767. Min Range: -2.1767
Max Act: 2.1767. Min Act: -0.1700
Data Index: 4800681 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1767. Min Range: -2.1767
Max Act: 2.1601. Min Act: -0.1700
Data Index: 1101342 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1767. Min Range: -2.1767
Max Act: 2.1767. Min Act: -0.1700
Data Index: 7838799 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1767. Min Range: -2.1767
Max Act: 2.1601. Min Act: -0.1700
Data Index: 1101344 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1767. Min Range: -2.1767
Max Act: 2.1434. Min Act: -0.1700
Data Index: 5359829 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1767. Min Range: -2.1767
Max Act: 2.1601. Min Act: -0.1700
Data Index: 5677475 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1767. Min Range: -2.1767
Max Act: 2.1434. Min Act: -0.1700
Data Index: 2176701 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1767. Min Range: -2.1767
Max Act: 2.1267. Min Act: -0.1700
Data Index: 2497495 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1767. Min Range: -2.1767
Max Act: 2.1267. Min Act: -0.1700
Data Index: 7216145 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1767. Min Range: -2.1767
Max Act: 2.1267. Min Act: -0.1700
Data Index: 3940571 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1767. Min Range: -2.1767
Max Act: 2.1267. Min Act: -0.1700
Data Index: 1862344 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1767. Min Range: -2.1767
Max Act: 2.0933. Min Act: -0.1700
Data Index: 1034043 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1767. Min Range: -2.1767
Max Act: 2.1100. Min Act: -0.1700
Data Index: 2370053 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1767. Min Range: -2.1767
Max Act: 2.1267. Min Act: -0.1700
Data Index: 7047850 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1767. Min Range: -2.1767
Max Act: 2.1100. Min Act: -0.1700
Data Index: 2944703 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1767. Min Range: -2.1767
Max Act: 2.0933. Min Act: -0.1700
Data Index: 3830260 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1767. Min Range: -2.1767
Max Act: 2.0933. Min Act: -0.1700
Data Index: 5713917 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1767. Min Range: -2.1767
Max Act: 2.1100. Min Act: -0.1700
Data Index: 2955205 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1767. Min Range: -2.1767
Max Act: 2.1100. Min Act: -0.1700
Data Index: 5594947 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1767. Min Range: -2.1767
Max Act: 2.0933. Min Act: -0.1700
Data Index: 1803914 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #19