Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2456 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.0926. Min Range: -8.0926
Max Act: 8.0301. Min Act: -0.1700
Data Index: 2459049 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0926. Min Range: -8.0926
Max Act: 8.0926. Min Act: -0.1700
Data Index: 4858250 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0926. Min Range: -8.0926
Max Act: 8.0301. Min Act: -0.1700
Data Index: 2064483 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0926. Min Range: -8.0926
Max Act: 7.8426. Min Act: -0.1700
Data Index: 194812 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0926. Min Range: -8.0926
Max Act: 7.9051. Min Act: -0.1700
Data Index: 8711093 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0926. Min Range: -8.0926
Max Act: 7.9051. Min Act: -0.1700
Data Index: 7987897 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0926. Min Range: -8.0926
Max Act: 7.9051. Min Act: -0.1700
Data Index: 926308 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0926. Min Range: -8.0926
Max Act: 7.9051. Min Act: -0.1700
Data Index: 3429189 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0926. Min Range: -8.0926
Max Act: 7.8426. Min Act: -0.1700
Data Index: 6622118 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0926. Min Range: -8.0926
Max Act: 7.8426. Min Act: -0.1700
Data Index: 6623792 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0926. Min Range: -8.0926
Max Act: 7.8426. Min Act: -0.1700
Data Index: 5723486 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0926. Min Range: -8.0926
Max Act: 7.8113. Min Act: -0.1700
Data Index: 7781250 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0926. Min Range: -8.0926
Max Act: 7.8113. Min Act: -0.1700
Data Index: 1050683 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0926. Min Range: -8.0926
Max Act: 7.8113. Min Act: -0.1700
Data Index: 2380940 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0926. Min Range: -8.0926
Max Act: 7.7801. Min Act: -0.1700
Data Index: 83134 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0926. Min Range: -8.0926
Max Act: 7.7801. Min Act: -0.1700
Data Index: 7995680 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0926. Min Range: -8.0926
Max Act: 7.6863. Min Act: -0.1700
Data Index: 2140416 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0926. Min Range: -8.0926
Max Act: 7.6863. Min Act: -0.1700
Data Index: 3033684 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0926. Min Range: -8.0926
Max Act: 7.7176. Min Act: -0.1700
Data Index: 5784903 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0926. Min Range: -8.0926
Max Act: 7.6863. Min Act: -0.1700
Data Index: 467806 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #19