Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3998 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.3471. Min Range: -5.3471
Max Act: 5.3471. Min Act: -0.1700
Data Index: 3022691 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3471. Min Range: -5.3471
Max Act: 5.3471. Min Act: -0.1700
Data Index: 204587 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3471. Min Range: -5.3471
Max Act: 5.0346. Min Act: -0.1700
Data Index: 1830144 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3471. Min Range: -5.3471
Max Act: 4.9721. Min Act: -0.1700
Data Index: 5620881 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3471. Min Range: -5.3471
Max Act: 4.8471. Min Act: -0.1700
Data Index: 6954391 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3471. Min Range: -5.3471
Max Act: 4.8783. Min Act: -0.1700
Data Index: 2334375 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3471. Min Range: -5.3471
Max Act: 4.9096. Min Act: -0.1700
Data Index: 706951 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3471. Min Range: -5.3471
Max Act: 4.8783. Min Act: -0.1700
Data Index: 1183388 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3471. Min Range: -5.3471
Max Act: 4.7533. Min Act: -0.1700
Data Index: 3876654 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3471. Min Range: -5.3471
Max Act: 4.7221. Min Act: -0.1700
Data Index: 4446405 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3471. Min Range: -5.3471
Max Act: 4.7533. Min Act: -0.1700
Data Index: 6317566 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3471. Min Range: -5.3471
Max Act: 4.7221. Min Act: -0.1700
Data Index: 6923514 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3471. Min Range: -5.3471
Max Act: 4.7221. Min Act: -0.1700
Data Index: 6358898 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3471. Min Range: -5.3471
Max Act: 4.7221. Min Act: -0.1700
Data Index: 4908736 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3471. Min Range: -5.3471
Max Act: 4.7221. Min Act: -0.1700
Data Index: 7606812 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3471. Min Range: -5.3471
Max Act: 4.7221. Min Act: -0.1700
Data Index: 5948416 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3471. Min Range: -5.3471
Max Act: 4.6908. Min Act: -0.1700
Data Index: 8407321 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3471. Min Range: -5.3471
Max Act: 4.6908. Min Act: -0.1700
Data Index: 3278275 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3471. Min Range: -5.3471
Max Act: 4.7221. Min Act: -0.1700
Data Index: 1026442 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3471. Min Range: -5.3471
Max Act: 4.7221. Min Act: -0.1700
Data Index: 3767770 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19