Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3168 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6680. Min Range: -7.6680
Max Act: 7.6680. Min Act: -0.1700
Data Index: 6900807 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6680. Min Range: -7.6680
Max Act: 7.5430. Min Act: -0.1700
Data Index: 7418359 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6680. Min Range: -7.6680
Max Act: 7.5117. Min Act: -0.1700
Data Index: 3322532 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6680. Min Range: -7.6680
Max Act: 7.2617. Min Act: -0.1700
Data Index: 6202420 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6680. Min Range: -7.6680
Max Act: 7.2617. Min Act: -0.1700
Data Index: 7207565 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6680. Min Range: -7.6680
Max Act: 7.2617. Min Act: -0.1700
Data Index: 2339338 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6680. Min Range: -7.6680
Max Act: 7.1992. Min Act: -0.1700
Data Index: 6988352 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6680. Min Range: -7.6680
Max Act: 7.1367. Min Act: -0.1700
Data Index: 4680059 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6680. Min Range: -7.6680
Max Act: 7.0742. Min Act: -0.1700
Data Index: 7383997 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6680. Min Range: -7.6680
Max Act: 7.0742. Min Act: -0.1700
Data Index: 2337109 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6680. Min Range: -7.6680
Max Act: 7.0742. Min Act: -0.1700
Data Index: 2006273 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6680. Min Range: -7.6680
Max Act: 7.0430. Min Act: -0.1700
Data Index: 218133 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6680. Min Range: -7.6680
Max Act: 7.0430. Min Act: -0.1700
Data Index: 5147426 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6680. Min Range: -7.6680
Max Act: 7.0430. Min Act: -0.1700
Data Index: 3433890 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6680. Min Range: -7.6680
Max Act: 7.0430. Min Act: -0.1700
Data Index: 4208896 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6680. Min Range: -7.6680
Max Act: 7.0117. Min Act: -0.1700
Data Index: 3295312 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6680. Min Range: -7.6680
Max Act: 7.0117. Min Act: -0.1700
Data Index: 2085763 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6680. Min Range: -7.6680
Max Act: 6.9805. Min Act: -0.1700
Data Index: 7035201 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6680. Min Range: -7.6680
Max Act: 7.0117. Min Act: -0.1700
Data Index: 1420541 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6680. Min Range: -7.6680
Max Act: 6.9805. Min Act: -0.1700
Data Index: 6951213 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #19