Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3799 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8721. Min Range: -5.8721
Max Act: 5.8721. Min Act: -0.1700
Data Index: 2434519 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8721. Min Range: -5.8721
Max Act: 5.7159. Min Act: -0.1700
Data Index: 8339959 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8721. Min Range: -5.8721
Max Act: 5.6846. Min Act: -0.1700
Data Index: 8414521 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8721. Min Range: -5.8721
Max Act: 5.6534. Min Act: -0.1700
Data Index: 1924497 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8721. Min Range: -5.8721
Max Act: 5.6221. Min Act: -0.1700
Data Index: 8569081 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8721. Min Range: -5.8721
Max Act: 5.6221. Min Act: -0.1700
Data Index: 1450714 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8721. Min Range: -5.8721
Max Act: 5.5596. Min Act: -0.1700
Data Index: 141452 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8721. Min Range: -5.8721
Max Act: 5.5596. Min Act: -0.1700
Data Index: 2329670 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8721. Min Range: -5.8721
Max Act: 5.5284. Min Act: -0.1700
Data Index: 8760128 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8721. Min Range: -5.8721
Max Act: 5.4971. Min Act: -0.1700
Data Index: 7322775 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8721. Min Range: -5.8721
Max Act: 5.4971. Min Act: -0.1700
Data Index: 8317565 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8721. Min Range: -5.8721
Max Act: 5.4971. Min Act: -0.1700
Data Index: 6354656 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8721. Min Range: -5.8721
Max Act: 5.4971. Min Act: -0.1700
Data Index: 4850214 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8721. Min Range: -5.8721
Max Act: 5.4659. Min Act: -0.1700
Data Index: 7283795 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8721. Min Range: -5.8721
Max Act: 5.4971. Min Act: -0.1700
Data Index: 1250577 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8721. Min Range: -5.8721
Max Act: 5.4659. Min Act: -0.1700
Data Index: 2555358 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8721. Min Range: -5.8721
Max Act: 5.4659. Min Act: -0.1700
Data Index: 489169 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8721. Min Range: -5.8721
Max Act: 5.4659. Min Act: -0.1700
Data Index: 1944890 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8721. Min Range: -5.8721
Max Act: 5.4346. Min Act: -0.1700
Data Index: 4257640 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8721. Min Range: -5.8721
Max Act: 5.4659. Min Act: -0.1700
Data Index: 4633387 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #19