Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5785 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8895. Min Range: -7.8895
Max Act: 7.8895. Min Act: -0.1700
Data Index: 5781655 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8895. Min Range: -7.8895
Max Act: 7.6395. Min Act: -0.1700
Data Index: 8436778 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8895. Min Range: -7.8895
Max Act: 7.6395. Min Act: -0.1700
Data Index: 2604998 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8895. Min Range: -7.8895
Max Act: 7.6083. Min Act: -0.1700
Data Index: 7967612 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8895. Min Range: -7.8895
Max Act: 7.5770. Min Act: -0.1700
Data Index: 5131928 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8895. Min Range: -7.8895
Max Act: 7.5458. Min Act: -0.1700
Data Index: 3450403 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8895. Min Range: -7.8895
Max Act: 7.5145. Min Act: -0.1700
Data Index: 565644 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8895. Min Range: -7.8895
Max Act: 7.4833. Min Act: -0.1700
Data Index: 4323608 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8895. Min Range: -7.8895
Max Act: 7.3895. Min Act: -0.1700
Data Index: 3504501 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8895. Min Range: -7.8895
Max Act: 7.3895. Min Act: -0.1700
Data Index: 3931475 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8895. Min Range: -7.8895
Max Act: 7.2958. Min Act: -0.1700
Data Index: 3911438 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8895. Min Range: -7.8895
Max Act: 7.2958. Min Act: -0.1700
Data Index: 2005114 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8895. Min Range: -7.8895
Max Act: 7.2958. Min Act: -0.1700
Data Index: 4138129 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8895. Min Range: -7.8895
Max Act: 7.2645. Min Act: -0.1700
Data Index: 1457782 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8895. Min Range: -7.8895
Max Act: 7.2020. Min Act: -0.1700
Data Index: 2636321 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8895. Min Range: -7.8895
Max Act: 7.2020. Min Act: -0.1700
Data Index: 8720043 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8895. Min Range: -7.8895
Max Act: 7.1708. Min Act: -0.1700
Data Index: 3480908 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8895. Min Range: -7.8895
Max Act: 7.1395. Min Act: -0.1700
Data Index: 7195628 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8895. Min Range: -7.8895
Max Act: 7.1395. Min Act: -0.1700
Data Index: 4409725 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8895. Min Range: -7.8895
Max Act: 7.0770. Min Act: -0.1700
Data Index: 4187252 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #19