Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5382 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.1778. Min Range: -9.1778
Max Act: 9.1778. Min Act: -0.1700
Data Index: 4605407 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1778. Min Range: -9.1778
Max Act: 9.1153. Min Act: -0.1700
Data Index: 6522656 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1778. Min Range: -9.1778
Max Act: 8.9903. Min Act: -0.1700
Data Index: 5519239 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1778. Min Range: -9.1778
Max Act: 8.7403. Min Act: -0.1700
Data Index: 7136828 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1778. Min Range: -9.1778
Max Act: 8.6778. Min Act: -0.1700
Data Index: 4810384 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1778. Min Range: -9.1778
Max Act: 8.6778. Min Act: -0.1700
Data Index: 1938273 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1778. Min Range: -9.1778
Max Act: 8.6778. Min Act: -0.1700
Data Index: 1576933 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1778. Min Range: -9.1778
Max Act: 8.6153. Min Act: -0.1700
Data Index: 3229761 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1778. Min Range: -9.1778
Max Act: 8.5528. Min Act: -0.1700
Data Index: 6272587 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1778. Min Range: -9.1778
Max Act: 8.6153. Min Act: -0.1700
Data Index: 2038488 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1778. Min Range: -9.1778
Max Act: 8.4903. Min Act: -0.1700
Data Index: 6165552 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1778. Min Range: -9.1778
Max Act: 8.4278. Min Act: -0.1700
Data Index: 2043244 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1778. Min Range: -9.1778
Max Act: 8.4278. Min Act: -0.1700
Data Index: 3875325 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1778. Min Range: -9.1778
Max Act: 8.4903. Min Act: -0.1700
Data Index: 2052003 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1778. Min Range: -9.1778
Max Act: 8.4278. Min Act: -0.1700
Data Index: 1858863 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1778. Min Range: -9.1778
Max Act: 8.4278. Min Act: -0.1700
Data Index: 4505692 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1778. Min Range: -9.1778
Max Act: 8.4278. Min Act: -0.1700
Data Index: 5505490 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1778. Min Range: -9.1778
Max Act: 8.3653. Min Act: -0.1700
Data Index: 3818881 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1778. Min Range: -9.1778
Max Act: 8.3653. Min Act: -0.1700
Data Index: 5229873 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1778. Min Range: -9.1778
Max Act: 8.3653. Min Act: -0.1700
Data Index: 5068896 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #19