Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 349 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.0602. Min Range: -7.0602
Max Act: 7.0602. Min Act: -0.1697
Data Index: 4146099 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0602. Min Range: -7.0602
Max Act: 6.9352. Min Act: -0.1700
Data Index: 2086406 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0602. Min Range: -7.0602
Max Act: 6.8727. Min Act: -0.1700
Data Index: 3145548 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0602. Min Range: -7.0602
Max Act: 6.8727. Min Act: -0.1700
Data Index: 7982596 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0602. Min Range: -7.0602
Max Act: 6.8102. Min Act: -0.1700
Data Index: 1355988 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0602. Min Range: -7.0602
Max Act: 6.8102. Min Act: -0.1700
Data Index: 1547978 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0602. Min Range: -7.0602
Max Act: 6.8102. Min Act: -0.1700
Data Index: 7982595 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0602. Min Range: -7.0602
Max Act: 6.8102. Min Act: -0.1700
Data Index: 7982597 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0602. Min Range: -7.0602
Max Act: 6.8102. Min Act: -0.1700
Data Index: 4988731 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0602. Min Range: -7.0602
Max Act: 6.8102. Min Act: -0.1700
Data Index: 2086407 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0602. Min Range: -7.0602
Max Act: 6.8102. Min Act: -0.1698
Data Index: 6693268 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0602. Min Range: -7.0602
Max Act: 6.8102. Min Act: -0.1700
Data Index: 1819169 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0602. Min Range: -7.0602
Max Act: 6.6852. Min Act: -0.1700
Data Index: 2297055 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0602. Min Range: -7.0602
Max Act: 6.7477. Min Act: -0.1700
Data Index: 953245 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0602. Min Range: -7.0602
Max Act: 6.7477. Min Act: -0.1700
Data Index: 7891941 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0602. Min Range: -7.0602
Max Act: 6.7477. Min Act: -0.1700
Data Index: 7530642 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0602. Min Range: -7.0602
Max Act: 6.7477. Min Act: -0.1700
Data Index: 8195720 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0602. Min Range: -7.0602
Max Act: 6.7477. Min Act: -0.1700
Data Index: 5663114 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0602. Min Range: -7.0602
Max Act: 6.6852. Min Act: -0.1700
Data Index: 1650485 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0602. Min Range: -7.0602
Max Act: 6.6852. Min Act: -0.1700
Data Index: 2839666 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #19