Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3004 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6149. Min Range: -7.6149
Max Act: 7.6149. Min Act: -0.1700
Data Index: 5992248 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6149. Min Range: -7.6149
Max Act: 7.5211. Min Act: -0.1700
Data Index: 6574033 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6149. Min Range: -7.6149
Max Act: 7.3961. Min Act: -0.1700
Data Index: 769814 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6149. Min Range: -7.6149
Max Act: 7.2086. Min Act: -0.1700
Data Index: 2743360 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6149. Min Range: -7.6149
Max Act: 7.2399. Min Act: -0.1700
Data Index: 7663372 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6149. Min Range: -7.6149
Max Act: 7.1774. Min Act: -0.1700
Data Index: 3236880 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6149. Min Range: -7.6149
Max Act: 7.1774. Min Act: -0.1700
Data Index: 1947736 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6149. Min Range: -7.6149
Max Act: 7.1461. Min Act: -0.1700
Data Index: 7849517 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6149. Min Range: -7.6149
Max Act: 7.1461. Min Act: -0.1700
Data Index: 2733166 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6149. Min Range: -7.6149
Max Act: 7.1149. Min Act: -0.1700
Data Index: 352151 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6149. Min Range: -7.6149
Max Act: 7.1149. Min Act: -0.1700
Data Index: 4782126 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6149. Min Range: -7.6149
Max Act: 7.1149. Min Act: -0.1700
Data Index: 797422 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6149. Min Range: -7.6149
Max Act: 7.1149. Min Act: -0.1700
Data Index: 3980533 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6149. Min Range: -7.6149
Max Act: 7.1149. Min Act: -0.1700
Data Index: 907548 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6149. Min Range: -7.6149
Max Act: 7.0836. Min Act: -0.1700
Data Index: 1397365 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6149. Min Range: -7.6149
Max Act: 7.0836. Min Act: -0.1700
Data Index: 5503804 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6149. Min Range: -7.6149
Max Act: 7.0524. Min Act: -0.1700
Data Index: 8352396 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6149. Min Range: -7.6149
Max Act: 7.0524. Min Act: -0.1700
Data Index: 8465918 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6149. Min Range: -7.6149
Max Act: 7.0524. Min Act: -0.1700
Data Index: 7619873 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6149. Min Range: -7.6149
Max Act: 7.0211. Min Act: -0.1700
Data Index: 6856691 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #19