Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5927 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5022. Min Range: -6.5022
Max Act: 6.5022. Min Act: -0.1700
Data Index: 4059485 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5022. Min Range: -6.5022
Max Act: 6.1585. Min Act: -0.1700
Data Index: 4271896 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5022. Min Range: -6.5022
Max Act: 5.9710. Min Act: -0.1700
Data Index: 8506195 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5022. Min Range: -6.5022
Max Act: 5.9710. Min Act: -0.1700
Data Index: 6562765 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5022. Min Range: -6.5022
Max Act: 5.9710. Min Act: -0.1700
Data Index: 4286449 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5022. Min Range: -6.5022
Max Act: 5.9710. Min Act: -0.1700
Data Index: 8812742 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5022. Min Range: -6.5022
Max Act: 5.9085. Min Act: -0.1700
Data Index: 4946757 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5022. Min Range: -6.5022
Max Act: 5.9085. Min Act: -0.1700
Data Index: 1495832 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5022. Min Range: -6.5022
Max Act: 5.8772. Min Act: -0.1700
Data Index: 2076094 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5022. Min Range: -6.5022
Max Act: 5.9085. Min Act: -0.1700
Data Index: 5293576 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5022. Min Range: -6.5022
Max Act: 5.8772. Min Act: -0.1700
Data Index: 2248020 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5022. Min Range: -6.5022
Max Act: 5.8772. Min Act: -0.1700
Data Index: 7116732 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5022. Min Range: -6.5022
Max Act: 5.8772. Min Act: -0.1700
Data Index: 2768153 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5022. Min Range: -6.5022
Max Act: 5.8772. Min Act: -0.1700
Data Index: 7288503 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5022. Min Range: -6.5022
Max Act: 5.8460. Min Act: -0.1700
Data Index: 870598 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5022. Min Range: -6.5022
Max Act: 5.8460. Min Act: -0.1700
Data Index: 2010046 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5022. Min Range: -6.5022
Max Act: 5.8460. Min Act: -0.1700
Data Index: 473996 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5022. Min Range: -6.5022
Max Act: 5.8460. Min Act: -0.1700
Data Index: 5941750 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5022. Min Range: -6.5022
Max Act: 5.8147. Min Act: -0.1700
Data Index: 3189599 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5022. Min Range: -6.5022
Max Act: 5.8147. Min Act: -0.1700
Data Index: 5608705 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #19