Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5406 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3607. Min Range: -6.3607
Max Act: 6.3607. Min Act: -0.1700
Data Index: 5415570 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3607. Min Range: -6.3607
Max Act: 6.3294. Min Act: -0.1700
Data Index: 358485 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3607. Min Range: -6.3607
Max Act: 6.2982. Min Act: -0.1700
Data Index: 2101405 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3607. Min Range: -6.3607
Max Act: 6.2044. Min Act: -0.1700
Data Index: 4370233 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3607. Min Range: -6.3607
Max Act: 6.1732. Min Act: -0.1700
Data Index: 3292685 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3607. Min Range: -6.3607
Max Act: 6.1732. Min Act: -0.1700
Data Index: 2000360 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3607. Min Range: -6.3607
Max Act: 6.1732. Min Act: -0.1700
Data Index: 1191517 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3607. Min Range: -6.3607
Max Act: 6.1732. Min Act: -0.1700
Data Index: 1191528 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3607. Min Range: -6.3607
Max Act: 6.0794. Min Act: -0.1700
Data Index: 1933911 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3607. Min Range: -6.3607
Max Act: 6.0794. Min Act: -0.1700
Data Index: 459097 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3607. Min Range: -6.3607
Max Act: 6.0482. Min Act: -0.1700
Data Index: 2011765 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3607. Min Range: -6.3607
Max Act: 6.0482. Min Act: -0.1700
Data Index: 7561387 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3607. Min Range: -6.3607
Max Act: 6.0169. Min Act: -0.1700
Data Index: 6520737 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3607. Min Range: -6.3607
Max Act: 6.0169. Min Act: -0.1700
Data Index: 2665724 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3607. Min Range: -6.3607
Max Act: 5.9544. Min Act: -0.1700
Data Index: 7204696 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3607. Min Range: -6.3607
Max Act: 5.8919. Min Act: -0.1700
Data Index: 1861240 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3607. Min Range: -6.3607
Max Act: 5.9544. Min Act: -0.1700
Data Index: 8797080 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3607. Min Range: -6.3607
Max Act: 5.9544. Min Act: -0.1700
Data Index: 7809411 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3607. Min Range: -6.3607
Max Act: 5.8919. Min Act: -0.1700
Data Index: 2518300 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3607. Min Range: -6.3607
Max Act: 5.9232. Min Act: -0.1700
Data Index: 490876 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #19