Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 317 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7617. Min Range: -7.7617
Max Act: 7.7617. Min Act: -0.1700
Data Index: 7938529 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7617. Min Range: -7.7617
Max Act: 7.6680. Min Act: -0.1700
Data Index: 5801973 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7617. Min Range: -7.7617
Max Act: 7.6680. Min Act: -0.1700
Data Index: 1714167 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7617. Min Range: -7.7617
Max Act: 7.6680. Min Act: -0.1700
Data Index: 3333973 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7617. Min Range: -7.7617
Max Act: 7.5742. Min Act: -0.1700
Data Index: 2971911 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7617. Min Range: -7.7617
Max Act: 7.5742. Min Act: -0.1700
Data Index: 2397273 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7617. Min Range: -7.7617
Max Act: 7.5430. Min Act: -0.1700
Data Index: 3513946 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7617. Min Range: -7.7617
Max Act: 7.4805. Min Act: -0.1700
Data Index: 2376282 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7617. Min Range: -7.7617
Max Act: 7.4805. Min Act: -0.1700
Data Index: 4851562 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7617. Min Range: -7.7617
Max Act: 7.4492. Min Act: -0.1700
Data Index: 2624935 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7617. Min Range: -7.7617
Max Act: 7.4492. Min Act: -0.1700
Data Index: 5178530 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7617. Min Range: -7.7617
Max Act: 7.4180. Min Act: -0.1700
Data Index: 8313186 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7617. Min Range: -7.7617
Max Act: 7.4492. Min Act: -0.1700
Data Index: 456038 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7617. Min Range: -7.7617
Max Act: 7.4180. Min Act: -0.1700
Data Index: 2833147 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7617. Min Range: -7.7617
Max Act: 7.4180. Min Act: -0.1700
Data Index: 2376281 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7617. Min Range: -7.7617
Max Act: 7.4180. Min Act: -0.1700
Data Index: 2072262 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7617. Min Range: -7.7617
Max Act: 7.3867. Min Act: -0.1700
Data Index: 5861308 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7617. Min Range: -7.7617
Max Act: 7.3867. Min Act: -0.1700
Data Index: 276433 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7617. Min Range: -7.7617
Max Act: 7.3867. Min Act: -0.1700
Data Index: 1112394 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7617. Min Range: -7.7617
Max Act: 7.4180. Min Act: -0.1700
Data Index: 4584317 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #19