Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5993 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8587. Min Range: -3.8587
Max Act: 3.8587. Min Act: -0.1700
Data Index: 5056509 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8587. Min Range: -3.8587
Max Act: 3.7648. Min Act: -0.1700
Data Index: 7093744 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8587. Min Range: -3.8587
Max Act: 3.7023. Min Act: -0.1700
Data Index: 1072386 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8587. Min Range: -3.8587
Max Act: 3.6397. Min Act: -0.1700
Data Index: 7770275 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8587. Min Range: -3.8587
Max Act: 3.5927. Min Act: -0.1700
Data Index: 8603286 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8587. Min Range: -3.8587
Max Act: 3.5771. Min Act: -0.1700
Data Index: 8077238 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8587. Min Range: -3.8587
Max Act: 3.5614. Min Act: -0.1700
Data Index: 2309704 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8587. Min Range: -3.8587
Max Act: 3.5614. Min Act: -0.1700
Data Index: 8645957 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8587. Min Range: -3.8587
Max Act: 3.5614. Min Act: -0.1700
Data Index: 4765475 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8587. Min Range: -3.8587
Max Act: 3.5771. Min Act: -0.1700
Data Index: 470409 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8587. Min Range: -3.8587
Max Act: 3.5614. Min Act: -0.1700
Data Index: 7381083 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8587. Min Range: -3.8587
Max Act: 3.5614. Min Act: -0.1700
Data Index: 3887754 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8587. Min Range: -3.8587
Max Act: 3.5614. Min Act: -0.1700
Data Index: 8718158 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8587. Min Range: -3.8587
Max Act: 3.5458. Min Act: -0.1700
Data Index: 2853586 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8587. Min Range: -3.8587
Max Act: 3.5458. Min Act: -0.1700
Data Index: 7925715 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8587. Min Range: -3.8587
Max Act: 3.5301. Min Act: -0.1700
Data Index: 3881782 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8587. Min Range: -3.8587
Max Act: 3.5145. Min Act: -0.1700
Data Index: 4140705 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8587. Min Range: -3.8587
Max Act: 3.4988. Min Act: -0.1700
Data Index: 5798692 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8587. Min Range: -3.8587
Max Act: 3.4831. Min Act: -0.1700
Data Index: 2489945 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8587. Min Range: -3.8587
Max Act: 3.4831. Min Act: -0.1700
Data Index: 1523647 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #19