Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4247 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3155. Min Range: -8.3155
Max Act: 8.3155. Min Act: -0.1700
Data Index: 5592808 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3155. Min Range: -8.3155
Max Act: 8.2530. Min Act: -0.1700
Data Index: 5726511 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3155. Min Range: -8.3155
Max Act: 8.2530. Min Act: -0.1700
Data Index: 8316885 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3155. Min Range: -8.3155
Max Act: 8.2218. Min Act: -0.1700
Data Index: 5592816 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3155. Min Range: -8.3155
Max Act: 8.2218. Min Act: -0.1700
Data Index: 8316878 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3155. Min Range: -8.3155
Max Act: 8.1593. Min Act: -0.1700
Data Index: 5726520 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3155. Min Range: -8.3155
Max Act: 8.1593. Min Act: -0.1700
Data Index: 3480270 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3155. Min Range: -8.3155
Max Act: 8.1280. Min Act: -0.1700
Data Index: 348343 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3155. Min Range: -8.3155
Max Act: 8.0968. Min Act: -0.1700
Data Index: 8068944 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3155. Min Range: -8.3155
Max Act: 8.0968. Min Act: -0.1700
Data Index: 3480281 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3155. Min Range: -8.3155
Max Act: 8.0030. Min Act: -0.1700
Data Index: 693911 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3155. Min Range: -8.3155
Max Act: 7.9718. Min Act: -0.1700
Data Index: 7622379 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3155. Min Range: -8.3155
Max Act: 8.0030. Min Act: -0.1700
Data Index: 8068930 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3155. Min Range: -8.3155
Max Act: 7.9405. Min Act: -0.1700
Data Index: 7622370 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3155. Min Range: -8.3155
Max Act: 7.9405. Min Act: -0.1700
Data Index: 8538331 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3155. Min Range: -8.3155
Max Act: 7.9093. Min Act: -0.1700
Data Index: 8538319 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3155. Min Range: -8.3155
Max Act: 7.9093. Min Act: -0.1700
Data Index: 388841 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3155. Min Range: -8.3155
Max Act: 7.8468. Min Act: -0.1700
Data Index: 388831 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3155. Min Range: -8.3155
Max Act: 7.8780. Min Act: -0.1700
Data Index: 693901 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3155. Min Range: -8.3155
Max Act: 7.8780. Min Act: -0.1700
Data Index: 1343722 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #19