Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2620 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2048. Min Range: -6.2048
Max Act: 6.2048. Min Act: -0.1700
Data Index: 3485767 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2048. Min Range: -6.2048
Max Act: 6.1736. Min Act: -0.1700
Data Index: 5311341 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2048. Min Range: -6.2048
Max Act: 6.0798. Min Act: -0.1700
Data Index: 3600697 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2048. Min Range: -6.2048
Max Act: 6.0798. Min Act: -0.1700
Data Index: 8132718 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2048. Min Range: -6.2048
Max Act: 6.0173. Min Act: -0.1700
Data Index: 6313025 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2048. Min Range: -6.2048
Max Act: 5.9548. Min Act: -0.1700
Data Index: 8306555 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2048. Min Range: -6.2048
Max Act: 5.9548. Min Act: -0.1700
Data Index: 1448076 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2048. Min Range: -6.2048
Max Act: 5.8923. Min Act: -0.1700
Data Index: 381063 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2048. Min Range: -6.2048
Max Act: 5.8923. Min Act: -0.1700
Data Index: 4652280 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2048. Min Range: -6.2048
Max Act: 5.8923. Min Act: -0.1700
Data Index: 3932829 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2048. Min Range: -6.2048
Max Act: 5.8923. Min Act: -0.1700
Data Index: 5667477 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2048. Min Range: -6.2048
Max Act: 5.8923. Min Act: -0.1699
Data Index: 7834973 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2048. Min Range: -6.2048
Max Act: 5.8298. Min Act: -0.1700
Data Index: 4841288 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2048. Min Range: -6.2048
Max Act: 5.8298. Min Act: -0.1700
Data Index: 4883815 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2048. Min Range: -6.2048
Max Act: 5.8298. Min Act: -0.1700
Data Index: 5302466 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2048. Min Range: -6.2048
Max Act: 5.8611. Min Act: -0.1700
Data Index: 159322 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2048. Min Range: -6.2048
Max Act: 5.8298. Min Act: -0.1700
Data Index: 1129226 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2048. Min Range: -6.2048
Max Act: 5.7673. Min Act: -0.1700
Data Index: 5089955 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2048. Min Range: -6.2048
Max Act: 5.7986. Min Act: -0.1700
Data Index: 3200492 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2048. Min Range: -6.2048
Max Act: 5.7673. Min Act: -0.1700
Data Index: 3537148 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #19