Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1499 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7835. Min Range: -6.7835
Max Act: 6.7835. Min Act: -0.1700
Data Index: 5624841 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7835. Min Range: -6.7835
Max Act: 6.7523. Min Act: -0.1700
Data Index: 6218063 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7835. Min Range: -6.7835
Max Act: 6.6898. Min Act: -0.1700
Data Index: 1255209 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7835. Min Range: -6.7835
Max Act: 6.6898. Min Act: -0.1700
Data Index: 3206114 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7835. Min Range: -6.7835
Max Act: 6.6898. Min Act: -0.1700
Data Index: 2248371 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7835. Min Range: -6.7835
Max Act: 6.6898. Min Act: -0.1700
Data Index: 513101 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7835. Min Range: -6.7835
Max Act: 6.6273. Min Act: -0.1700
Data Index: 830889 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7835. Min Range: -6.7835
Max Act: 6.5960. Min Act: -0.1700
Data Index: 4180731 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7835. Min Range: -6.7835
Max Act: 6.5960. Min Act: -0.1700
Data Index: 2022993 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7835. Min Range: -6.7835
Max Act: 6.5648. Min Act: -0.1700
Data Index: 2016429 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7835. Min Range: -6.7835
Max Act: 6.5648. Min Act: -0.1700
Data Index: 624891 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7835. Min Range: -6.7835
Max Act: 6.5648. Min Act: -0.1700
Data Index: 7302079 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7835. Min Range: -6.7835
Max Act: 6.5648. Min Act: -0.1700
Data Index: 3795374 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7835. Min Range: -6.7835
Max Act: 6.5335. Min Act: -0.1700
Data Index: 6585884 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7835. Min Range: -6.7835
Max Act: 6.5335. Min Act: -0.1700
Data Index: 7651767 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7835. Min Range: -6.7835
Max Act: 6.5023. Min Act: -0.1700
Data Index: 6781407 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7835. Min Range: -6.7835
Max Act: 6.5023. Min Act: -0.1700
Data Index: 1780556 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7835. Min Range: -6.7835
Max Act: 6.5023. Min Act: -0.1700
Data Index: 6582247 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7835. Min Range: -6.7835
Max Act: 6.4710. Min Act: -0.1700
Data Index: 3781404 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7835. Min Range: -6.7835
Max Act: 6.5023. Min Act: -0.1700
Data Index: 2124425 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #19