Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6087 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9341. Min Range: -3.9341
Max Act: 3.9341. Min Act: -0.1700
Data Index: 4946577 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9341. Min Range: -3.9341
Max Act: 3.8559. Min Act: -0.1700
Data Index: 619682 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9341. Min Range: -3.9341
Max Act: 3.8715. Min Act: -0.1700
Data Index: 2630552 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9341. Min Range: -3.9341
Max Act: 3.8090. Min Act: -0.1700
Data Index: 4782218 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9341. Min Range: -3.9341
Max Act: 3.7777. Min Act: -0.1700
Data Index: 7967924 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9341. Min Range: -3.9341
Max Act: 3.7308. Min Act: -0.1700
Data Index: 4405601 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9341. Min Range: -3.9341
Max Act: 3.6839. Min Act: -0.1700
Data Index: 5898781 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9341. Min Range: -3.9341
Max Act: 3.6682. Min Act: -0.1700
Data Index: 3385787 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9341. Min Range: -3.9341
Max Act: 3.6682. Min Act: -0.1700
Data Index: 3764569 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9341. Min Range: -3.9341
Max Act: 3.6526. Min Act: -0.1700
Data Index: 1397245 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9341. Min Range: -3.9341
Max Act: 3.6526. Min Act: -0.1700
Data Index: 1945842 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9341. Min Range: -3.9341
Max Act: 3.6526. Min Act: -0.1700
Data Index: 252437 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9341. Min Range: -3.9341
Max Act: 3.6213. Min Act: -0.1700
Data Index: 6066246 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9341. Min Range: -3.9341
Max Act: 3.6213. Min Act: -0.1700
Data Index: 4338746 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9341. Min Range: -3.9341
Max Act: 3.6056. Min Act: -0.1700
Data Index: 8820580 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9341. Min Range: -3.9341
Max Act: 3.6213. Min Act: -0.1700
Data Index: 5146549 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9341. Min Range: -3.9341
Max Act: 3.5900. Min Act: -0.1700
Data Index: 4565468 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9341. Min Range: -3.9341
Max Act: 3.5900. Min Act: -0.1700
Data Index: 4588689 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9341. Min Range: -3.9341
Max Act: 3.6056. Min Act: -0.1700
Data Index: 7812118 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9341. Min Range: -3.9341
Max Act: 3.5900. Min Act: -0.1700
Data Index: 7737774 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #19