Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5229 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9055. Min Range: -6.9055
Max Act: 6.9055. Min Act: -0.1700
Data Index: 5334599 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9055. Min Range: -6.9055
Max Act: 6.8117. Min Act: -0.1700
Data Index: 7877385 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9055. Min Range: -6.9055
Max Act: 6.8117. Min Act: -0.1700
Data Index: 3275195 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9055. Min Range: -6.9055
Max Act: 6.7805. Min Act: -0.1700
Data Index: 133060 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9055. Min Range: -6.9055
Max Act: 6.6555. Min Act: -0.1700
Data Index: 7546712 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9055. Min Range: -6.9055
Max Act: 6.6555. Min Act: -0.1700
Data Index: 589482 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9055. Min Range: -6.9055
Max Act: 6.6242. Min Act: -0.1700
Data Index: 1187232 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9055. Min Range: -6.9055
Max Act: 6.5930. Min Act: -0.1700
Data Index: 7094129 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9055. Min Range: -6.9055
Max Act: 6.6242. Min Act: -0.1700
Data Index: 6083741 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9055. Min Range: -6.9055
Max Act: 6.5930. Min Act: -0.1700
Data Index: 6232599 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9055. Min Range: -6.9055
Max Act: 6.5617. Min Act: -0.1700
Data Index: 5075673 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9055. Min Range: -6.9055
Max Act: 6.5930. Min Act: -0.1700
Data Index: 6068806 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9055. Min Range: -6.9055
Max Act: 6.5617. Min Act: -0.1700
Data Index: 589484 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9055. Min Range: -6.9055
Max Act: 6.5617. Min Act: -0.1700
Data Index: 2081700 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9055. Min Range: -6.9055
Max Act: 6.5305. Min Act: -0.1700
Data Index: 7318684 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9055. Min Range: -6.9055
Max Act: 6.4992. Min Act: -0.1700
Data Index: 1484658 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9055. Min Range: -6.9055
Max Act: 6.5305. Min Act: -0.1700
Data Index: 6691078 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9055. Min Range: -6.9055
Max Act: 6.5617. Min Act: -0.1700
Data Index: 5069364 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9055. Min Range: -6.9055
Max Act: 6.5305. Min Act: -0.1700
Data Index: 473680 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9055. Min Range: -6.9055
Max Act: 6.5617. Min Act: -0.1700
Data Index: 3127827 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #19