Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1603 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5149. Min Range: -3.5149
Max Act: 3.5149. Min Act: -0.1700
Data Index: 422937 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5149. Min Range: -3.5149
Max Act: 3.5149. Min Act: -0.1700
Data Index: 2520825 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5149. Min Range: -3.5149
Max Act: 3.4679. Min Act: -0.1700
Data Index: 9032 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5149. Min Range: -3.5149
Max Act: 3.4679. Min Act: -0.1700
Data Index: 3187398 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5149. Min Range: -3.5149
Max Act: 3.4679. Min Act: -0.1700
Data Index: 5042614 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5149. Min Range: -3.5149
Max Act: 3.3895. Min Act: -0.1700
Data Index: 6346481 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5149. Min Range: -3.5149
Max Act: 3.3738. Min Act: -0.1700
Data Index: 3827004 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5149. Min Range: -3.5149
Max Act: 3.3738. Min Act: -0.1700
Data Index: 3692457 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5149. Min Range: -3.5149
Max Act: 3.3268. Min Act: -0.1700
Data Index: 2181993 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5149. Min Range: -3.5149
Max Act: 3.2954. Min Act: -0.1700
Data Index: 3469938 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5149. Min Range: -3.5149
Max Act: 3.2954. Min Act: -0.1700
Data Index: 7407862 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5149. Min Range: -3.5149
Max Act: 3.2954. Min Act: -0.1700
Data Index: 2754723 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5149. Min Range: -3.5149
Max Act: 3.2797. Min Act: -0.1700
Data Index: 2058329 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5149. Min Range: -3.5149
Max Act: 3.2954. Min Act: -0.1700
Data Index: 5099335 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5149. Min Range: -3.5149
Max Act: 3.2954. Min Act: -0.1700
Data Index: 1933994 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5149. Min Range: -3.5149
Max Act: 3.2954. Min Act: -0.1700
Data Index: 2404916 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5149. Min Range: -3.5149
Max Act: 3.2797. Min Act: -0.1700
Data Index: 4195357 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5149. Min Range: -3.5149
Max Act: 3.2797. Min Act: -0.1700
Data Index: 904126 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5149. Min Range: -3.5149
Max Act: 3.2640. Min Act: -0.1700
Data Index: 3836422 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5149. Min Range: -3.5149
Max Act: 3.2640. Min Act: -0.1700
Data Index: 4379108 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #19