Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2781 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5410. Min Range: -4.5410
Max Act: 4.5410. Min Act: -0.1700
Data Index: 2735424 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5410. Min Range: -4.5410
Max Act: 4.5410. Min Act: -0.1700
Data Index: 7914933 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5410. Min Range: -4.5410
Max Act: 4.5098. Min Act: -0.1700
Data Index: 999447 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5410. Min Range: -4.5410
Max Act: 4.4785. Min Act: -0.1700
Data Index: 3151418 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5410. Min Range: -4.5410
Max Act: 4.4785. Min Act: -0.1700
Data Index: 4019829 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5410. Min Range: -4.5410
Max Act: 4.4785. Min Act: -0.1700
Data Index: 4981624 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5410. Min Range: -4.5410
Max Act: 4.4785. Min Act: -0.1700
Data Index: 1638807 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5410. Min Range: -4.5410
Max Act: 4.4473. Min Act: -0.1700
Data Index: 57595 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5410. Min Range: -4.5410
Max Act: 4.4473. Min Act: -0.1700
Data Index: 1810119 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5410. Min Range: -4.5410
Max Act: 4.4473. Min Act: -0.1700
Data Index: 3530043 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5410. Min Range: -4.5410
Max Act: 4.4473. Min Act: -0.1700
Data Index: 823224 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5410. Min Range: -4.5410
Max Act: 4.4473. Min Act: -0.1700
Data Index: 8232698 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5410. Min Range: -4.5410
Max Act: 4.4160. Min Act: -0.1700
Data Index: 4424443 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5410. Min Range: -4.5410
Max Act: 4.4160. Min Act: -0.1700
Data Index: 4673116 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5410. Min Range: -4.5410
Max Act: 4.4160. Min Act: -0.1700
Data Index: 7080209 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5410. Min Range: -4.5410
Max Act: 4.4473. Min Act: -0.1700
Data Index: 5911796 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5410. Min Range: -4.5410
Max Act: 4.4160. Min Act: -0.1700
Data Index: 5573027 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5410. Min Range: -4.5410
Max Act: 4.3848. Min Act: -0.1700
Data Index: 1638837 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5410. Min Range: -4.5410
Max Act: 4.3848. Min Act: -0.1700
Data Index: 4851114 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5410. Min Range: -4.5410
Max Act: 4.3848. Min Act: -0.1700
Data Index: 4961343 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #19