Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4517 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.3968. Min Range: -9.3968
Max Act: 9.3968. Min Act: -0.1700
Data Index: 5404027 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3968. Min Range: -9.3968
Max Act: 9.1468. Min Act: -0.1700
Data Index: 5609784 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3968. Min Range: -9.3968
Max Act: 9.0843. Min Act: -0.1700
Data Index: 159843 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3968. Min Range: -9.3968
Max Act: 8.9593. Min Act: -0.1700
Data Index: 3246398 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3968. Min Range: -9.3968
Max Act: 8.8968. Min Act: -0.1700
Data Index: 545287 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3968. Min Range: -9.3968
Max Act: 8.8968. Min Act: -0.1700
Data Index: 692331 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3968. Min Range: -9.3968
Max Act: 8.8968. Min Act: -0.1700
Data Index: 107797 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3968. Min Range: -9.3968
Max Act: 8.8343. Min Act: -0.1700
Data Index: 7792180 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3968. Min Range: -9.3968
Max Act: 8.8343. Min Act: -0.1700
Data Index: 5937773 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3968. Min Range: -9.3968
Max Act: 8.8343. Min Act: -0.1700
Data Index: 2123343 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3968. Min Range: -9.3968
Max Act: 8.7718. Min Act: -0.1700
Data Index: 3171335 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3968. Min Range: -9.3968
Max Act: 8.7093. Min Act: -0.1700
Data Index: 6050761 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3968. Min Range: -9.3968
Max Act: 8.7093. Min Act: -0.1700
Data Index: 4470595 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3968. Min Range: -9.3968
Max Act: 8.7093. Min Act: -0.1700
Data Index: 4161214 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3968. Min Range: -9.3968
Max Act: 8.6468. Min Act: -0.1700
Data Index: 5482297 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3968. Min Range: -9.3968
Max Act: 8.6468. Min Act: -0.1700
Data Index: 4041542 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3968. Min Range: -9.3968
Max Act: 8.6468. Min Act: -0.1700
Data Index: 6158245 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3968. Min Range: -9.3968
Max Act: 8.6468. Min Act: -0.1700
Data Index: 2336332 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3968. Min Range: -9.3968
Max Act: 8.5843. Min Act: -0.1700
Data Index: 2121893 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3968. Min Range: -9.3968
Max Act: 8.5843. Min Act: -0.1700
Data Index: 887320 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #19