Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4247 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 26.2580. Min Range: -26.2580
Max Act: 26.2580. Min Act: -0.1700
Data Index: 4321330 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 26.2580. Min Range: -26.2580
Max Act: 25.8830. Min Act: -0.1700
Data Index: 8150291 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 26.2580. Min Range: -26.2580
Max Act: 25.6330. Min Act: -0.1700
Data Index: 5599217 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 26.2580. Min Range: -26.2580
Max Act: 25.6330. Min Act: -0.1700
Data Index: 5345881 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 26.2580. Min Range: -26.2580
Max Act: 25.3830. Min Act: -0.1700
Data Index: 5974188 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 26.2580. Min Range: -26.2580
Max Act: 25.5080. Min Act: -0.1699
Data Index: 3687476 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 26.2580. Min Range: -26.2580
Max Act: 25.3830. Min Act: -0.1700
Data Index: 5110277 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 26.2580. Min Range: -26.2580
Max Act: 25.3830. Min Act: -0.1700
Data Index: 7912933 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 26.2580. Min Range: -26.2580
Max Act: 25.3830. Min Act: -0.1700
Data Index: 3975687 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 26.2580. Min Range: -26.2580
Max Act: 25.3830. Min Act: -0.1700
Data Index: 2697721 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 26.2580. Min Range: -26.2580
Max Act: 25.2580. Min Act: -0.1700
Data Index: 442675 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 26.2580. Min Range: -26.2580
Max Act: 25.3830. Min Act: -0.1700
Data Index: 1810888 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 26.2580. Min Range: -26.2580
Max Act: 25.2580. Min Act: -0.1700
Data Index: 3415982 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 26.2580. Min Range: -26.2580
Max Act: 25.2580. Min Act: -0.1700
Data Index: 5639403 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 26.2580. Min Range: -26.2580
Max Act: 25.1330. Min Act: -0.1700
Data Index: 481304 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 26.2580. Min Range: -26.2580
Max Act: 25.1330. Min Act: -0.1700
Data Index: 1965960 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 26.2580. Min Range: -26.2580
Max Act: 25.0080. Min Act: -0.1700
Data Index: 1693443 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 26.2580. Min Range: -26.2580
Max Act: 24.8830. Min Act: -0.1700
Data Index: 2235737 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 26.2580. Min Range: -26.2580
Max Act: 24.8830. Min Act: -0.1700
Data Index: 3332061 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 26.2580. Min Range: -26.2580
Max Act: 24.7580. Min Act: -0.1700
Data Index: 4894899 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #19