Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5782 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6605. Min Range: -7.6605
Max Act: 7.6605. Min Act: -0.1700
Data Index: 4885561 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6605. Min Range: -7.6605
Max Act: 7.5355. Min Act: -0.1700
Data Index: 6063009 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6605. Min Range: -7.6605
Max Act: 7.4105. Min Act: -0.1700
Data Index: 4093894 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6605. Min Range: -7.6605
Max Act: 7.4105. Min Act: -0.1700
Data Index: 2278004 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6605. Min Range: -7.6605
Max Act: 7.4105. Min Act: -0.1700
Data Index: 4885560 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6605. Min Range: -7.6605
Max Act: 7.4105. Min Act: -0.1700
Data Index: 1152770 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6605. Min Range: -7.6605
Max Act: 7.3480. Min Act: -0.1700
Data Index: 220657 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6605. Min Range: -7.6605
Max Act: 7.3480. Min Act: -0.1700
Data Index: 7026829 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6605. Min Range: -7.6605
Max Act: 7.3480. Min Act: -0.1700
Data Index: 3230337 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6605. Min Range: -7.6605
Max Act: 7.3480. Min Act: -0.1700
Data Index: 7026828 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6605. Min Range: -7.6605
Max Act: 7.2855. Min Act: -0.1700
Data Index: 4093893 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6605. Min Range: -7.6605
Max Act: 7.3480. Min Act: -0.1700
Data Index: 3073790 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6605. Min Range: -7.6605
Max Act: 7.3480. Min Act: -0.1700
Data Index: 3230329 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6605. Min Range: -7.6605
Max Act: 7.2855. Min Act: -0.1700
Data Index: 2329898 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6605. Min Range: -7.6605
Max Act: 7.3480. Min Act: -0.1700
Data Index: 7234525 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6605. Min Range: -7.6605
Max Act: 7.2855. Min Act: -0.1700
Data Index: 5405764 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6605. Min Range: -7.6605
Max Act: 7.2855. Min Act: -0.1700
Data Index: 4001878 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6605. Min Range: -7.6605
Max Act: 7.2855. Min Act: -0.1700
Data Index: 6545558 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6605. Min Range: -7.6605
Max Act: 7.2230. Min Act: -0.1700
Data Index: 4885562 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6605. Min Range: -7.6605
Max Act: 7.2230. Min Act: -0.1700
Data Index: 3230326 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #19