Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3404 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8824. Min Range: -6.8824
Max Act: 6.8824. Min Act: -0.1700
Data Index: 4244791 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8824. Min Range: -6.8824
Max Act: 6.6636. Min Act: -0.1700
Data Index: 2651507 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8824. Min Range: -6.8824
Max Act: 6.6011. Min Act: -0.1700
Data Index: 3036828 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8824. Min Range: -6.8824
Max Act: 6.6011. Min Act: -0.1700
Data Index: 482413 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8824. Min Range: -6.8824
Max Act: 6.5699. Min Act: -0.1700
Data Index: 3690465 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8824. Min Range: -6.8824
Max Act: 6.3511. Min Act: -0.1700
Data Index: 354571 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8824. Min Range: -6.8824
Max Act: 6.3199. Min Act: -0.1700
Data Index: 3430096 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8824. Min Range: -6.8824
Max Act: 6.2886. Min Act: -0.1700
Data Index: 2156428 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8824. Min Range: -6.8824
Max Act: 6.2886. Min Act: -0.1700
Data Index: 6155856 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8824. Min Range: -6.8824
Max Act: 6.2574. Min Act: -0.1700
Data Index: 5784543 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8824. Min Range: -6.8824
Max Act: 6.2574. Min Act: -0.1700
Data Index: 6143791 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8824. Min Range: -6.8824
Max Act: 6.2261. Min Act: -0.1700
Data Index: 6948045 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8824. Min Range: -6.8824
Max Act: 6.2261. Min Act: -0.1700
Data Index: 3439999 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8824. Min Range: -6.8824
Max Act: 6.2261. Min Act: -0.1700
Data Index: 5465499 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8824. Min Range: -6.8824
Max Act: 6.2261. Min Act: -0.1700
Data Index: 4481097 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8824. Min Range: -6.8824
Max Act: 6.1949. Min Act: -0.1700
Data Index: 1634544 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8824. Min Range: -6.8824
Max Act: 6.1949. Min Act: -0.1700
Data Index: 6274442 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8824. Min Range: -6.8824
Max Act: 6.1949. Min Act: -0.1700
Data Index: 4721903 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8824. Min Range: -6.8824
Max Act: 6.1949. Min Act: -0.1700
Data Index: 3591859 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8824. Min Range: -6.8824
Max Act: 6.1949. Min Act: -0.1700
Data Index: 4192327 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #19