Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2936 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.7800. Min Range: -5.7800
Max Act: 5.7800. Min Act: -0.1700
Data Index: 2847203 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7800. Min Range: -5.7800
Max Act: 5.7800. Min Act: -0.1700
Data Index: 3194700 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7800. Min Range: -5.7800
Max Act: 5.6237. Min Act: -0.1700
Data Index: 3625924 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7800. Min Range: -5.7800
Max Act: 5.5300. Min Act: -0.1700
Data Index: 6030640 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7800. Min Range: -5.7800
Max Act: 5.4675. Min Act: -0.1700
Data Index: 5523074 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7800. Min Range: -5.7800
Max Act: 5.5300. Min Act: -0.1700
Data Index: 4211869 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7800. Min Range: -5.7800
Max Act: 5.4362. Min Act: -0.1700
Data Index: 8090128 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7800. Min Range: -5.7800
Max Act: 5.4050. Min Act: -0.1700
Data Index: 7253762 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7800. Min Range: -5.7800
Max Act: 5.3112. Min Act: -0.1700
Data Index: 6574852 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7800. Min Range: -5.7800
Max Act: 5.3425. Min Act: -0.1700
Data Index: 7253761 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7800. Min Range: -5.7800
Max Act: 5.2800. Min Act: -0.1700
Data Index: 4590244 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7800. Min Range: -5.7800
Max Act: 5.3425. Min Act: -0.1700
Data Index: 3381327 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7800. Min Range: -5.7800
Max Act: 5.3112. Min Act: -0.1700
Data Index: 1858379 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7800. Min Range: -5.7800
Max Act: 5.3112. Min Act: -0.1700
Data Index: 3434642 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7800. Min Range: -5.7800
Max Act: 5.3112. Min Act: -0.1700
Data Index: 6254903 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7800. Min Range: -5.7800
Max Act: 5.2487. Min Act: -0.1700
Data Index: 4575664 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7800. Min Range: -5.7800
Max Act: 5.2800. Min Act: -0.1700
Data Index: 2750742 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7800. Min Range: -5.7800
Max Act: 5.3112. Min Act: -0.1700
Data Index: 4748139 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7800. Min Range: -5.7800
Max Act: 5.2487. Min Act: -0.1700
Data Index: 4926726 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7800. Min Range: -5.7800
Max Act: 5.2800. Min Act: -0.1700
Data Index: 2081936 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #19