Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3950 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.2028. Min Range: -9.2028
Max Act: 9.2028. Min Act: -0.1700
Data Index: 7158877 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.2028. Min Range: -9.2028
Max Act: 9.2028. Min Act: -0.1700
Data Index: 3410790 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.2028. Min Range: -9.2028
Max Act: 9.1403. Min Act: -0.1700
Data Index: 19345 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.2028. Min Range: -9.2028
Max Act: 9.0778. Min Act: -0.1700
Data Index: 6908792 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.2028. Min Range: -9.2028
Max Act: 9.0153. Min Act: -0.1700
Data Index: 2975866 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.2028. Min Range: -9.2028
Max Act: 8.9528. Min Act: -0.1700
Data Index: 1104389 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.2028. Min Range: -9.2028
Max Act: 8.9528. Min Act: -0.1700
Data Index: 4799282 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.2028. Min Range: -9.2028
Max Act: 8.9528. Min Act: -0.1700
Data Index: 6953703 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.2028. Min Range: -9.2028
Max Act: 8.8903. Min Act: -0.1700
Data Index: 1976257 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.2028. Min Range: -9.2028
Max Act: 8.7653. Min Act: -0.1700
Data Index: 4494188 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.2028. Min Range: -9.2028
Max Act: 8.7028. Min Act: -0.1700
Data Index: 7687603 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.2028. Min Range: -9.2028
Max Act: 8.6403. Min Act: -0.1700
Data Index: 2253148 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.2028. Min Range: -9.2028
Max Act: 8.6403. Min Act: -0.1700
Data Index: 7995425 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.2028. Min Range: -9.2028
Max Act: 8.6403. Min Act: -0.1700
Data Index: 8667830 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.2028. Min Range: -9.2028
Max Act: 8.6403. Min Act: -0.1700
Data Index: 6558401 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.2028. Min Range: -9.2028
Max Act: 8.5153. Min Act: -0.1700
Data Index: 3608822 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.2028. Min Range: -9.2028
Max Act: 8.5778. Min Act: -0.1700
Data Index: 4467952 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.2028. Min Range: -9.2028
Max Act: 8.5153. Min Act: -0.1700
Data Index: 1431260 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.2028. Min Range: -9.2028
Max Act: 8.5153. Min Act: -0.1700
Data Index: 6946908 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.2028. Min Range: -9.2028
Max Act: 8.5153. Min Act: -0.1700
Data Index: 4155977 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #19