Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3404 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.2388. Min Range: -2.2388
Max Act: 2.2388. Min Act: -0.1700
Data Index: 6163226 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2388. Min Range: -2.2388
Max Act: 2.2056. Min Act: -0.1700
Data Index: 6008523 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2388. Min Range: -2.2388
Max Act: 2.1724. Min Act: -0.1700
Data Index: 8689251 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2388. Min Range: -2.2388
Max Act: 2.1558. Min Act: -0.1700
Data Index: 8293398 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2388. Min Range: -2.2388
Max Act: 2.1224. Min Act: -0.1700
Data Index: 6106593 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2388. Min Range: -2.2388
Max Act: 2.1224. Min Act: -0.1700
Data Index: 8288631 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2388. Min Range: -2.2388
Max Act: 2.1224. Min Act: -0.1700
Data Index: 1365000 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2388. Min Range: -2.2388
Max Act: 2.1224. Min Act: -0.1700
Data Index: 5599042 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2388. Min Range: -2.2388
Max Act: 2.0889. Min Act: -0.1700
Data Index: 7764858 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2388. Min Range: -2.2388
Max Act: 2.0889. Min Act: -0.1700
Data Index: 4038898 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2388. Min Range: -2.2388
Max Act: 2.0721. Min Act: -0.1700
Data Index: 6246384 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2388. Min Range: -2.2388
Max Act: 2.0721. Min Act: -0.1700
Data Index: 1572183 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2388. Min Range: -2.2388
Max Act: 2.0721. Min Act: -0.1700
Data Index: 3091146 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2388. Min Range: -2.2388
Max Act: 2.0721. Min Act: -0.1700
Data Index: 2905879 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2388. Min Range: -2.2388
Max Act: 2.0721. Min Act: -0.1700
Data Index: 2843097 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2388. Min Range: -2.2388
Max Act: 2.0721. Min Act: -0.1700
Data Index: 8295503 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2388. Min Range: -2.2388
Max Act: 2.0721. Min Act: -0.1700
Data Index: 5422695 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2388. Min Range: -2.2388
Max Act: 2.0721. Min Act: -0.1700
Data Index: 3100025 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2388. Min Range: -2.2388
Max Act: 2.0553. Min Act: -0.1700
Data Index: 2244675 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2388. Min Range: -2.2388
Max Act: 2.0553. Min Act: -0.1700
Data Index: 4069100 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #19