Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2909 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8160. Min Range: -8.8160
Max Act: 8.8160. Min Act: -0.1700
Data Index: 4396499 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8160. Min Range: -8.8160
Max Act: 8.6910. Min Act: -0.1700
Data Index: 4396501 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8160. Min Range: -8.8160
Max Act: 8.3785. Min Act: -0.1700
Data Index: 1900552 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8160. Min Range: -8.8160
Max Act: 8.4410. Min Act: -0.1700
Data Index: 6055458 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8160. Min Range: -8.8160
Max Act: 8.4410. Min Act: -0.1700
Data Index: 268113 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8160. Min Range: -8.8160
Max Act: 8.3785. Min Act: -0.1700
Data Index: 5463583 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8160. Min Range: -8.8160
Max Act: 8.3785. Min Act: -0.1700
Data Index: 3112103 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8160. Min Range: -8.8160
Max Act: 8.3160. Min Act: -0.1700
Data Index: 2765793 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8160. Min Range: -8.8160
Max Act: 8.3785. Min Act: -0.1700
Data Index: 4594312 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8160. Min Range: -8.8160
Max Act: 8.3160. Min Act: -0.1700
Data Index: 5378563 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8160. Min Range: -8.8160
Max Act: 8.3160. Min Act: -0.1700
Data Index: 6814856 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8160. Min Range: -8.8160
Max Act: 8.2535. Min Act: -0.1700
Data Index: 4504702 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8160. Min Range: -8.8160
Max Act: 8.2535. Min Act: -0.1700
Data Index: 1554525 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8160. Min Range: -8.8160
Max Act: 8.2535. Min Act: -0.1700
Data Index: 7628996 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8160. Min Range: -8.8160
Max Act: 8.1910. Min Act: -0.1700
Data Index: 6546389 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8160. Min Range: -8.8160
Max Act: 8.1910. Min Act: -0.1700
Data Index: 1700306 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8160. Min Range: -8.8160
Max Act: 8.1910. Min Act: -0.1700
Data Index: 5946157 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8160. Min Range: -8.8160
Max Act: 8.1910. Min Act: -0.1700
Data Index: 5625554 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8160. Min Range: -8.8160
Max Act: 8.1910. Min Act: -0.1700
Data Index: 5432103 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8160. Min Range: -8.8160
Max Act: 8.1285. Min Act: -0.1700
Data Index: 1633563 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #19