Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4031 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.0065. Min Range: -10.0065
Max Act: 10.0065. Min Act: -0.1700
Data Index: 3915339 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.0065. Min Range: -10.0065
Max Act: 9.5690. Min Act: -0.1700
Data Index: 6739130 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.0065. Min Range: -10.0065
Max Act: 9.4440. Min Act: -0.1700
Data Index: 6902324 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.0065. Min Range: -10.0065
Max Act: 9.3190. Min Act: -0.1700
Data Index: 7361786 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.0065. Min Range: -10.0065
Max Act: 9.3190. Min Act: -0.1700
Data Index: 7119760 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.0065. Min Range: -10.0065
Max Act: 9.2565. Min Act: -0.1700
Data Index: 789094 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.0065. Min Range: -10.0065
Max Act: 9.1940. Min Act: -0.1700
Data Index: 7451278 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.0065. Min Range: -10.0065
Max Act: 9.1940. Min Act: -0.1700
Data Index: 7716174 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.0065. Min Range: -10.0065
Max Act: 9.1940. Min Act: -0.1700
Data Index: 5999785 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.0065. Min Range: -10.0065
Max Act: 9.1940. Min Act: -0.1700
Data Index: 2694146 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.0065. Min Range: -10.0065
Max Act: 9.1315. Min Act: -0.1700
Data Index: 3282854 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.0065. Min Range: -10.0065
Max Act: 9.0690. Min Act: -0.1700
Data Index: 1178520 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.0065. Min Range: -10.0065
Max Act: 9.1315. Min Act: -0.1700
Data Index: 2254349 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.0065. Min Range: -10.0065
Max Act: 9.0690. Min Act: -0.1700
Data Index: 1001947 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.0065. Min Range: -10.0065
Max Act: 9.0690. Min Act: -0.1700
Data Index: 5543132 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.0065. Min Range: -10.0065
Max Act: 9.0690. Min Act: -0.1700
Data Index: 4910599 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.0065. Min Range: -10.0065
Max Act: 9.0690. Min Act: -0.1700
Data Index: 1497735 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.0065. Min Range: -10.0065
Max Act: 9.0690. Min Act: -0.1700
Data Index: 785094 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.0065. Min Range: -10.0065
Max Act: 8.9440. Min Act: -0.1700
Data Index: 4104612 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.0065. Min Range: -10.0065
Max Act: 8.9440. Min Act: -0.1700
Data Index: 658115 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #19