Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3584 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0820. Min Range: -9.0820
Max Act: 9.0820. Min Act: -0.1700
Data Index: 3623697 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0820. Min Range: -9.0820
Max Act: 9.0820. Min Act: -0.1700
Data Index: 3458266 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0820. Min Range: -9.0820
Max Act: 8.9570. Min Act: -0.1700
Data Index: 7766563 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0820. Min Range: -9.0820
Max Act: 8.9570. Min Act: -0.1700
Data Index: 6114716 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0820. Min Range: -9.0820
Max Act: 8.8945. Min Act: -0.1700
Data Index: 1416575 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0820. Min Range: -9.0820
Max Act: 8.8945. Min Act: -0.1700
Data Index: 4270744 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0820. Min Range: -9.0820
Max Act: 8.8320. Min Act: -0.1700
Data Index: 8231936 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0820. Min Range: -9.0820
Max Act: 8.8945. Min Act: -0.1700
Data Index: 7652776 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0820. Min Range: -9.0820
Max Act: 8.8945. Min Act: -0.1700
Data Index: 3521512 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0820. Min Range: -9.0820
Max Act: 8.8320. Min Act: -0.1700
Data Index: 714699 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0820. Min Range: -9.0820
Max Act: 8.7695. Min Act: -0.1700
Data Index: 4448986 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0820. Min Range: -9.0820
Max Act: 8.8320. Min Act: -0.1700
Data Index: 1370453 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0820. Min Range: -9.0820
Max Act: 8.7695. Min Act: -0.1700
Data Index: 3169274 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0820. Min Range: -9.0820
Max Act: 8.7695. Min Act: -0.1700
Data Index: 999841 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0820. Min Range: -9.0820
Max Act: 8.7070. Min Act: -0.1700
Data Index: 3169275 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0820. Min Range: -9.0820
Max Act: 8.7695. Min Act: -0.1700
Data Index: 2489386 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0820. Min Range: -9.0820
Max Act: 8.7070. Min Act: -0.1700
Data Index: 685908 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0820. Min Range: -9.0820
Max Act: 8.7695. Min Act: -0.1700
Data Index: 4317364 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0820. Min Range: -9.0820
Max Act: 8.7695. Min Act: -0.1700
Data Index: 4667492 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0820. Min Range: -9.0820
Max Act: 8.7695. Min Act: -0.1700
Data Index: 4894878 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #19