Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5611 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 12.3495. Min Range: -12.3495
Max Act: 12.3495. Min Act: -0.1700
Data Index: 7618975 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.3495. Min Range: -12.3495
Max Act: 11.8495. Min Act: -0.1700
Data Index: 3032258 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.3495. Min Range: -12.3495
Max Act: 11.2245. Min Act: -0.1700
Data Index: 2264305 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.3495. Min Range: -12.3495
Max Act: 11.0370. Min Act: -0.1700
Data Index: 1121614 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.3495. Min Range: -12.3495
Max Act: 10.9745. Min Act: -0.1700
Data Index: 4512188 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.3495. Min Range: -12.3495
Max Act: 10.9745. Min Act: -0.1700
Data Index: 5390318 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.3495. Min Range: -12.3495
Max Act: 10.9745. Min Act: -0.1700
Data Index: 618117 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.3495. Min Range: -12.3495
Max Act: 10.8495. Min Act: -0.1700
Data Index: 1483664 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.3495. Min Range: -12.3495
Max Act: 10.9120. Min Act: -0.1700
Data Index: 7262394 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.3495. Min Range: -12.3495
Max Act: 10.7870. Min Act: -0.1700
Data Index: 5597662 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.3495. Min Range: -12.3495
Max Act: 10.7870. Min Act: -0.1700
Data Index: 1399835 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.3495. Min Range: -12.3495
Max Act: 10.7870. Min Act: -0.1700
Data Index: 7103721 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.3495. Min Range: -12.3495
Max Act: 10.6620. Min Act: -0.1700
Data Index: 1824738 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.3495. Min Range: -12.3495
Max Act: 10.5370. Min Act: -0.1700
Data Index: 8071228 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.3495. Min Range: -12.3495
Max Act: 10.5370. Min Act: -0.1700
Data Index: 2162998 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.3495. Min Range: -12.3495
Max Act: 10.4745. Min Act: -0.1700
Data Index: 602032 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.3495. Min Range: -12.3495
Max Act: 10.4745. Min Act: -0.1700
Data Index: 7299174 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.3495. Min Range: -12.3495
Max Act: 10.4745. Min Act: -0.1700
Data Index: 7365766 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.3495. Min Range: -12.3495
Max Act: 10.4745. Min Act: -0.1700
Data Index: 2463613 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.3495. Min Range: -12.3495
Max Act: 10.3495. Min Act: -0.1700
Data Index: 4452357 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #19