Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4518 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.0271. Min Range: -3.0271
Max Act: 3.0271. Min Act: -0.1700
Data Index: 3380865 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0271. Min Range: -3.0271
Max Act: 2.9955. Min Act: -0.1700
Data Index: 6280261 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0271. Min Range: -3.0271
Max Act: 2.9955. Min Act: -0.1700
Data Index: 871875 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0271. Min Range: -3.0271
Max Act: 2.8846. Min Act: -0.1700
Data Index: 4017635 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0271. Min Range: -3.0271
Max Act: 2.8688. Min Act: -0.1700
Data Index: 2154031 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0271. Min Range: -3.0271
Max Act: 2.8211. Min Act: -0.1700
Data Index: 3719916 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0271. Min Range: -3.0271
Max Act: 2.7892. Min Act: -0.1700
Data Index: 7574466 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0271. Min Range: -3.0271
Max Act: 2.7733. Min Act: -0.1700
Data Index: 5381205 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0271. Min Range: -3.0271
Max Act: 2.7733. Min Act: -0.1700
Data Index: 7147162 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0271. Min Range: -3.0271
Max Act: 2.7733. Min Act: -0.1700
Data Index: 4660922 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0271. Min Range: -3.0271
Max Act: 2.7892. Min Act: -0.1700
Data Index: 5826614 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0271. Min Range: -3.0271
Max Act: 2.7414. Min Act: -0.1700
Data Index: 2812185 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0271. Min Range: -3.0271
Max Act: 2.7414. Min Act: -0.1700
Data Index: 6248913 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0271. Min Range: -3.0271
Max Act: 2.7574. Min Act: -0.1700
Data Index: 961377 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0271. Min Range: -3.0271
Max Act: 2.7574. Min Act: -0.1700
Data Index: 199078 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0271. Min Range: -3.0271
Max Act: 2.7094. Min Act: -0.1700
Data Index: 2962378 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0271. Min Range: -3.0271
Max Act: 2.7094. Min Act: -0.1700
Data Index: 969313 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0271. Min Range: -3.0271
Max Act: 2.7094. Min Act: -0.1700
Data Index: 775045 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0271. Min Range: -3.0271
Max Act: 2.7094. Min Act: -0.1700
Data Index: 5759116 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0271. Min Range: -3.0271
Max Act: 2.7094. Min Act: -0.1700
Data Index: 5850831 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #19