Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 331 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3732. Min Range: -6.3732
Max Act: 6.3732. Min Act: -0.1700
Data Index: 1351433 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3732. Min Range: -6.3732
Max Act: 6.3419. Min Act: -0.1700
Data Index: 7230866 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3732. Min Range: -6.3732
Max Act: 6.3419. Min Act: -0.1700
Data Index: 7674614 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3732. Min Range: -6.3732
Max Act: 6.2482. Min Act: -0.1700
Data Index: 1373563 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3732. Min Range: -6.3732
Max Act: 6.1544. Min Act: -0.1700
Data Index: 6628869 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3732. Min Range: -6.3732
Max Act: 6.1232. Min Act: -0.1700
Data Index: 3488855 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3732. Min Range: -6.3732
Max Act: 6.1232. Min Act: -0.1700
Data Index: 5062309 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3732. Min Range: -6.3732
Max Act: 6.0919. Min Act: -0.1700
Data Index: 8598476 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3732. Min Range: -6.3732
Max Act: 6.0294. Min Act: -0.1700
Data Index: 6246318 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3732. Min Range: -6.3732
Max Act: 5.9982. Min Act: -0.1700
Data Index: 4549619 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3732. Min Range: -6.3732
Max Act: 5.9982. Min Act: -0.1700
Data Index: 4811744 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3732. Min Range: -6.3732
Max Act: 5.9669. Min Act: -0.1700
Data Index: 4811730 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3732. Min Range: -6.3732
Max Act: 5.9357. Min Act: -0.1700
Data Index: 7844963 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3732. Min Range: -6.3732
Max Act: 5.9044. Min Act: -0.1700
Data Index: 1040154 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3732. Min Range: -6.3732
Max Act: 5.9044. Min Act: -0.1700
Data Index: 4811729 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3732. Min Range: -6.3732
Max Act: 5.9044. Min Act: -0.1700
Data Index: 7141586 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3732. Min Range: -6.3732
Max Act: 5.8732. Min Act: -0.1700
Data Index: 4811734 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3732. Min Range: -6.3732
Max Act: 5.8732. Min Act: -0.1700
Data Index: 5317432 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3732. Min Range: -6.3732
Max Act: 5.8419. Min Act: -0.1700
Data Index: 7844956 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3732. Min Range: -6.3732
Max Act: 5.8732. Min Act: -0.1700
Data Index: 5605272 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #19