Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2446 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.1890. Min Range: -5.1890
Max Act: 5.1890. Min Act: -0.1700
Data Index: 6608550 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1890. Min Range: -5.1890
Max Act: 5.1577. Min Act: -0.1700
Data Index: 3303278 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1890. Min Range: -5.1890
Max Act: 5.1890. Min Act: -0.1700
Data Index: 7172609 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1890. Min Range: -5.1890
Max Act: 5.1890. Min Act: -0.1700
Data Index: 5154451 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1890. Min Range: -5.1890
Max Act: 5.1577. Min Act: -0.1700
Data Index: 713439 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1890. Min Range: -5.1890
Max Act: 5.1577. Min Act: -0.1700
Data Index: 1694220 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1890. Min Range: -5.1890
Max Act: 5.1265. Min Act: -0.1700
Data Index: 4221277 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1890. Min Range: -5.1890
Max Act: 5.1265. Min Act: -0.1700
Data Index: 614541 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1890. Min Range: -5.1890
Max Act: 5.1265. Min Act: -0.1700
Data Index: 2005158 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1890. Min Range: -5.1890
Max Act: 5.1265. Min Act: -0.1700
Data Index: 3330602 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1890. Min Range: -5.1890
Max Act: 5.1265. Min Act: -0.1700
Data Index: 2821651 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1890. Min Range: -5.1890
Max Act: 5.1265. Min Act: -0.1700
Data Index: 7374148 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1890. Min Range: -5.1890
Max Act: 5.1265. Min Act: -0.1700
Data Index: 6991135 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1890. Min Range: -5.1890
Max Act: 5.1890. Min Act: -0.1700
Data Index: 1724994 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1890. Min Range: -5.1890
Max Act: 5.1265. Min Act: -0.1700
Data Index: 2338363 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1890. Min Range: -5.1890
Max Act: 5.0952. Min Act: -0.1700
Data Index: 5757751 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1890. Min Range: -5.1890
Max Act: 5.0952. Min Act: -0.1700
Data Index: 7999210 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1890. Min Range: -5.1890
Max Act: 5.1265. Min Act: -0.1700
Data Index: 8584710 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1890. Min Range: -5.1890
Max Act: 5.0640. Min Act: -0.1700
Data Index: 1805076 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1890. Min Range: -5.1890
Max Act: 5.0640. Min Act: -0.1700
Data Index: 6044995 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #19