Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 12 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3026. Min Range: -4.3026
Max Act: 4.3026. Min Act: -0.1700
Data Index: 7425499 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3026. Min Range: -4.3026
Max Act: 4.1463. Min Act: -0.1700
Data Index: 7764276 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3026. Min Range: -4.3026
Max Act: 4.1151. Min Act: -0.1700
Data Index: 307728 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3026. Min Range: -4.3026
Max Act: 4.0838. Min Act: -0.1700
Data Index: 8680707 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3026. Min Range: -4.3026
Max Act: 4.0838. Min Act: -0.1700
Data Index: 34737 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3026. Min Range: -4.3026
Max Act: 4.0213. Min Act: -0.1700
Data Index: 5019383 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3026. Min Range: -4.3026
Max Act: 4.0213. Min Act: -0.1700
Data Index: 1242964 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3026. Min Range: -4.3026
Max Act: 3.9900. Min Act: -0.1700
Data Index: 4478245 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3026. Min Range: -4.3026
Max Act: 3.9900. Min Act: -0.1700
Data Index: 7881746 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3026. Min Range: -4.3026
Max Act: 3.9588. Min Act: -0.1700
Data Index: 5620848 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3026. Min Range: -4.3026
Max Act: 3.9588. Min Act: -0.1700
Data Index: 7522242 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3026. Min Range: -4.3026
Max Act: 3.8962. Min Act: -0.1700
Data Index: 6603553 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3026. Min Range: -4.3026
Max Act: 3.8962. Min Act: -0.1700
Data Index: 207381 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3026. Min Range: -4.3026
Max Act: 3.8962. Min Act: -0.1700
Data Index: 5691420 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3026. Min Range: -4.3026
Max Act: 3.8962. Min Act: -0.1700
Data Index: 1478507 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3026. Min Range: -4.3026
Max Act: 3.8650. Min Act: -0.1700
Data Index: 2767220 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3026. Min Range: -4.3026
Max Act: 3.8962. Min Act: -0.1700
Data Index: 5994210 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3026. Min Range: -4.3026
Max Act: 3.8650. Min Act: -0.1700
Data Index: 3614337 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3026. Min Range: -4.3026
Max Act: 3.8650. Min Act: -0.1700
Data Index: 4531758 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3026. Min Range: -4.3026
Max Act: 3.8650. Min Act: -0.1700
Data Index: 8105687 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #19