Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3010 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1155. Min Range: -8.1155
Max Act: 8.1155. Min Act: -0.1700
Data Index: 7873520 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1155. Min Range: -8.1155
Max Act: 8.0218. Min Act: -0.1700
Data Index: 669082 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1155. Min Range: -8.1155
Max Act: 7.9280. Min Act: -0.1700
Data Index: 6627916 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1155. Min Range: -8.1155
Max Act: 7.7718. Min Act: -0.1700
Data Index: 4505814 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1155. Min Range: -8.1155
Max Act: 7.7093. Min Act: -0.1700
Data Index: 1772144 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1155. Min Range: -8.1155
Max Act: 7.7405. Min Act: -0.1700
Data Index: 2753578 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1155. Min Range: -8.1155
Max Act: 7.7093. Min Act: -0.1700
Data Index: 6574851 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1155. Min Range: -8.1155
Max Act: 7.7405. Min Act: -0.1700
Data Index: 2477021 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1155. Min Range: -8.1155
Max Act: 7.6780. Min Act: -0.1700
Data Index: 8476410 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1155. Min Range: -8.1155
Max Act: 7.6780. Min Act: -0.1699
Data Index: 6244631 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1155. Min Range: -8.1155
Max Act: 7.7093. Min Act: -0.1700
Data Index: 8354507 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1155. Min Range: -8.1155
Max Act: 7.6468. Min Act: -0.1700
Data Index: 3350190 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1155. Min Range: -8.1155
Max Act: 7.6155. Min Act: -0.1700
Data Index: 3047281 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1155. Min Range: -8.1155
Max Act: 7.5843. Min Act: -0.1700
Data Index: 4937941 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1155. Min Range: -8.1155
Max Act: 7.5530. Min Act: -0.1700
Data Index: 2686136 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1155. Min Range: -8.1155
Max Act: 7.5530. Min Act: -0.1700
Data Index: 4111024 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1155. Min Range: -8.1155
Max Act: 7.5218. Min Act: -0.1700
Data Index: 5581676 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1155. Min Range: -8.1155
Max Act: 7.4905. Min Act: -0.1700
Data Index: 5757223 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1155. Min Range: -8.1155
Max Act: 7.4280. Min Act: -0.1700
Data Index: 2212317 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1155. Min Range: -8.1155
Max Act: 7.4280. Min Act: -0.1700
Data Index: 3716216 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #19