Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4590 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3124. Min Range: -5.3124
Max Act: 5.3124. Min Act: -0.1700
Data Index: 2333143 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3124. Min Range: -5.3124
Max Act: 5.3124. Min Act: -0.1700
Data Index: 6616355 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3124. Min Range: -5.3124
Max Act: 5.3124. Min Act: -0.1700
Data Index: 6251109 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3124. Min Range: -5.3124
Max Act: 5.2186. Min Act: -0.1700
Data Index: 4990139 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3124. Min Range: -5.3124
Max Act: 5.2186. Min Act: -0.1700
Data Index: 4334961 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3124. Min Range: -5.3124
Max Act: 5.2499. Min Act: -0.1700
Data Index: 3813781 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3124. Min Range: -5.3124
Max Act: 5.2186. Min Act: -0.1700
Data Index: 5045241 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3124. Min Range: -5.3124
Max Act: 5.2186. Min Act: -0.1700
Data Index: 7132278 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3124. Min Range: -5.3124
Max Act: 5.1874. Min Act: -0.1700
Data Index: 3813782 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3124. Min Range: -5.3124
Max Act: 5.1874. Min Act: -0.1700
Data Index: 6616349 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3124. Min Range: -5.3124
Max Act: 5.1874. Min Act: -0.1700
Data Index: 4632357 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3124. Min Range: -5.3124
Max Act: 5.1561. Min Act: -0.1700
Data Index: 8019780 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3124. Min Range: -5.3124
Max Act: 5.1561. Min Act: -0.1700
Data Index: 934533 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3124. Min Range: -5.3124
Max Act: 5.1874. Min Act: -0.1700
Data Index: 3813786 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3124. Min Range: -5.3124
Max Act: 5.1561. Min Act: -0.1700
Data Index: 1691813 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3124. Min Range: -5.3124
Max Act: 5.1249. Min Act: -0.1700
Data Index: 394419 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3124. Min Range: -5.3124
Max Act: 5.1249. Min Act: -0.1700
Data Index: 4538176 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3124. Min Range: -5.3124
Max Act: 5.1249. Min Act: -0.1700
Data Index: 5100053 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3124. Min Range: -5.3124
Max Act: 5.1561. Min Act: -0.1700
Data Index: 1795968 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3124. Min Range: -5.3124
Max Act: 5.1249. Min Act: -0.1700
Data Index: 4306793 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #19