Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3386 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.3929. Min Range: -4.3929
Max Act: 4.3616. Min Act: -0.1700
Data Index: 7288163 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3929. Min Range: -4.3929
Max Act: 4.3929. Min Act: -0.1700
Data Index: 1164351 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3929. Min Range: -4.3929
Max Act: 4.3304. Min Act: -0.1700
Data Index: 3829253 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3929. Min Range: -4.3929
Max Act: 4.2991. Min Act: -0.1700
Data Index: 4818463 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3929. Min Range: -4.3929
Max Act: 4.3304. Min Act: -0.1700
Data Index: 7700384 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3929. Min Range: -4.3929
Max Act: 4.2679. Min Act: -0.1700
Data Index: 8756753 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3929. Min Range: -4.3929
Max Act: 4.2679. Min Act: -0.1700
Data Index: 7104977 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3929. Min Range: -4.3929
Max Act: 4.2679. Min Act: -0.1700
Data Index: 5859353 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3929. Min Range: -4.3929
Max Act: 4.2679. Min Act: -0.1700
Data Index: 4686126 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3929. Min Range: -4.3929
Max Act: 4.2366. Min Act: -0.1700
Data Index: 2968167 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3929. Min Range: -4.3929
Max Act: 4.2679. Min Act: -0.1700
Data Index: 8562839 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3929. Min Range: -4.3929
Max Act: 4.2053. Min Act: -0.1700
Data Index: 693997 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3929. Min Range: -4.3929
Max Act: 4.1741. Min Act: -0.1700
Data Index: 2822199 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3929. Min Range: -4.3929
Max Act: 4.1116. Min Act: -0.1700
Data Index: 4368273 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3929. Min Range: -4.3929
Max Act: 4.1428. Min Act: -0.1700
Data Index: 3187417 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3929. Min Range: -4.3929
Max Act: 4.1428. Min Act: -0.1700
Data Index: 2397790 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3929. Min Range: -4.3929
Max Act: 4.1428. Min Act: -0.1700
Data Index: 432019 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3929. Min Range: -4.3929
Max Act: 4.1116. Min Act: -0.1700
Data Index: 5894651 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3929. Min Range: -4.3929
Max Act: 4.1428. Min Act: -0.1700
Data Index: 6103166 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3929. Min Range: -4.3929
Max Act: 4.1428. Min Act: -0.1700
Data Index: 1199593 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #19