Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3685 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.2830. Min Range: -5.2830
Max Act: 5.2830. Min Act: -0.1700
Data Index: 1325243 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2830. Min Range: -5.2830
Max Act: 5.0955. Min Act: -0.1700
Data Index: 7724972 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2830. Min Range: -5.2830
Max Act: 5.0642. Min Act: -0.1700
Data Index: 595827 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2830. Min Range: -5.2830
Max Act: 5.0642. Min Act: -0.1700
Data Index: 380994 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2830. Min Range: -5.2830
Max Act: 5.0642. Min Act: -0.1700
Data Index: 6774807 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2830. Min Range: -5.2830
Max Act: 5.0330. Min Act: -0.1700
Data Index: 1758814 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2830. Min Range: -5.2830
Max Act: 5.0330. Min Act: -0.1700
Data Index: 2854166 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2830. Min Range: -5.2830
Max Act: 5.0330. Min Act: -0.1700
Data Index: 8437947 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2830. Min Range: -5.2830
Max Act: 5.0017. Min Act: -0.1700
Data Index: 8139055 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2830. Min Range: -5.2830
Max Act: 4.9705. Min Act: -0.1700
Data Index: 6597008 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2830. Min Range: -5.2830
Max Act: 4.9392. Min Act: -0.1700
Data Index: 4748950 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2830. Min Range: -5.2830
Max Act: 4.9080. Min Act: -0.1700
Data Index: 23564 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2830. Min Range: -5.2830
Max Act: 4.8767. Min Act: -0.1700
Data Index: 4562789 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2830. Min Range: -5.2830
Max Act: 4.8767. Min Act: -0.1700
Data Index: 8323793 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2830. Min Range: -5.2830
Max Act: 4.8455. Min Act: -0.1700
Data Index: 4604094 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2830. Min Range: -5.2830
Max Act: 4.8455. Min Act: -0.1700
Data Index: 2172893 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2830. Min Range: -5.2830
Max Act: 4.8767. Min Act: -0.1700
Data Index: 5681320 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2830. Min Range: -5.2830
Max Act: 4.8455. Min Act: -0.1700
Data Index: 4396818 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2830. Min Range: -5.2830
Max Act: 4.8142. Min Act: -0.1700
Data Index: 5511149 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2830. Min Range: -5.2830
Max Act: 4.8142. Min Act: -0.1700
Data Index: 4664122 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #19