Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2998 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8338. Min Range: -5.8338
Max Act: 5.8338. Min Act: -0.1700
Data Index: 1446860 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8338. Min Range: -5.8338
Max Act: 5.7400. Min Act: -0.1700
Data Index: 7385502 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8338. Min Range: -5.8338
Max Act: 5.6150. Min Act: -0.1700
Data Index: 4876462 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8338. Min Range: -5.8338
Max Act: 5.5525. Min Act: -0.1700
Data Index: 4731306 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8338. Min Range: -5.8338
Max Act: 5.5838. Min Act: -0.1700
Data Index: 4389016 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8338. Min Range: -5.8338
Max Act: 5.5838. Min Act: -0.1700
Data Index: 4876461 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8338. Min Range: -5.8338
Max Act: 5.5525. Min Act: -0.1700
Data Index: 1160448 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8338. Min Range: -5.8338
Max Act: 5.5525. Min Act: -0.1700
Data Index: 7176963 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8338. Min Range: -5.8338
Max Act: 5.5525. Min Act: -0.1700
Data Index: 8574749 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8338. Min Range: -5.8338
Max Act: 5.5525. Min Act: -0.1700
Data Index: 2702389 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8338. Min Range: -5.8338
Max Act: 5.5213. Min Act: -0.1700
Data Index: 2456469 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8338. Min Range: -5.8338
Max Act: 5.5213. Min Act: -0.1700
Data Index: 7130977 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8338. Min Range: -5.8338
Max Act: 5.4588. Min Act: -0.1700
Data Index: 7103884 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8338. Min Range: -5.8338
Max Act: 5.4900. Min Act: -0.1700
Data Index: 1665582 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8338. Min Range: -5.8338
Max Act: 5.4588. Min Act: -0.1700
Data Index: 3851817 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8338. Min Range: -5.8338
Max Act: 5.4275. Min Act: -0.1700
Data Index: 848372 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8338. Min Range: -5.8338
Max Act: 5.4275. Min Act: -0.1700
Data Index: 1517195 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8338. Min Range: -5.8338
Max Act: 5.4588. Min Act: -0.1700
Data Index: 5000345 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8338. Min Range: -5.8338
Max Act: 5.4588. Min Act: -0.1700
Data Index: 1704406 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8338. Min Range: -5.8338
Max Act: 5.4588. Min Act: -0.1700
Data Index: 1484474 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #19