Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2757 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5610. Min Range: -8.5610
Max Act: 8.4985. Min Act: -0.1700
Data Index: 5285484 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5610. Min Range: -8.5610
Max Act: 8.5610. Min Act: -0.1700
Data Index: 6663312 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5610. Min Range: -8.5610
Max Act: 8.3735. Min Act: -0.1700
Data Index: 7431786 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5610. Min Range: -8.5610
Max Act: 8.2485. Min Act: -0.1700
Data Index: 3876196 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5610. Min Range: -8.5610
Max Act: 8.2485. Min Act: -0.1700
Data Index: 3106498 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5610. Min Range: -8.5610
Max Act: 8.2485. Min Act: -0.1700
Data Index: 4211870 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5610. Min Range: -8.5610
Max Act: 8.1235. Min Act: -0.1700
Data Index: 8161187 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5610. Min Range: -8.5610
Max Act: 8.1235. Min Act: -0.1700
Data Index: 7118788 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5610. Min Range: -8.5610
Max Act: 8.0610. Min Act: -0.1700
Data Index: 3012653 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5610. Min Range: -8.5610
Max Act: 8.0610. Min Act: -0.1700
Data Index: 6302555 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5610. Min Range: -8.5610
Max Act: 7.9985. Min Act: -0.1700
Data Index: 4293559 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5610. Min Range: -8.5610
Max Act: 7.9360. Min Act: -0.1700
Data Index: 7170841 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5610. Min Range: -8.5610
Max Act: 7.9360. Min Act: -0.1700
Data Index: 1203781 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5610. Min Range: -8.5610
Max Act: 7.9360. Min Act: -0.1700
Data Index: 6469928 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5610. Min Range: -8.5610
Max Act: 7.8735. Min Act: -0.1700
Data Index: 3673103 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5610. Min Range: -8.5610
Max Act: 7.8735. Min Act: -0.1700
Data Index: 1096934 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5610. Min Range: -8.5610
Max Act: 7.8735. Min Act: -0.1700
Data Index: 4077316 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5610. Min Range: -8.5610
Max Act: 7.8735. Min Act: -0.1700
Data Index: 2100017 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5610. Min Range: -8.5610
Max Act: 7.8110. Min Act: -0.1700
Data Index: 5497384 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5610. Min Range: -8.5610
Max Act: 7.8110. Min Act: -0.1700
Data Index: 4617422 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #19