Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2958 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8692. Min Range: -6.8692
Max Act: 6.8692. Min Act: -0.1700
Data Index: 4506333 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8692. Min Range: -6.8692
Max Act: 6.8067. Min Act: -0.1700
Data Index: 3110568 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8692. Min Range: -6.8692
Max Act: 6.6817. Min Act: -0.1700
Data Index: 8432099 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8692. Min Range: -6.8692
Max Act: 6.6504. Min Act: -0.1700
Data Index: 839841 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8692. Min Range: -6.8692
Max Act: 6.4629. Min Act: -0.1700
Data Index: 2168404 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8692. Min Range: -6.8692
Max Act: 6.3692. Min Act: -0.1700
Data Index: 2892424 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8692. Min Range: -6.8692
Max Act: 6.3067. Min Act: -0.1700
Data Index: 6279283 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8692. Min Range: -6.8692
Max Act: 6.3067. Min Act: -0.1700
Data Index: 8020455 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8692. Min Range: -6.8692
Max Act: 6.2442. Min Act: -0.1700
Data Index: 3717824 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8692. Min Range: -6.8692
Max Act: 6.2754. Min Act: -0.1700
Data Index: 8688623 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8692. Min Range: -6.8692
Max Act: 6.2442. Min Act: -0.1700
Data Index: 3786273 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8692. Min Range: -6.8692
Max Act: 6.2442. Min Act: -0.1700
Data Index: 8228803 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8692. Min Range: -6.8692
Max Act: 6.1504. Min Act: -0.1700
Data Index: 5391729 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8692. Min Range: -6.8692
Max Act: 6.1504. Min Act: -0.1700
Data Index: 5202551 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8692. Min Range: -6.8692
Max Act: 6.0879. Min Act: -0.1700
Data Index: 1813103 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8692. Min Range: -6.8692
Max Act: 6.1504. Min Act: -0.1700
Data Index: 2134146 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8692. Min Range: -6.8692
Max Act: 6.1192. Min Act: -0.1700
Data Index: 3686186 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8692. Min Range: -6.8692
Max Act: 6.1504. Min Act: -0.1700
Data Index: 4312807 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8692. Min Range: -6.8692
Max Act: 6.1504. Min Act: -0.1700
Data Index: 8584810 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8692. Min Range: -6.8692
Max Act: 6.1192. Min Act: -0.1700
Data Index: 4891075 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #19