Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2516 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1660. Min Range: -4.1660
Max Act: 4.1660. Min Act: -0.1700
Data Index: 2135182 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1660. Min Range: -4.1660
Max Act: 4.1348. Min Act: -0.1700
Data Index: 8700841 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1660. Min Range: -4.1660
Max Act: 4.0722. Min Act: -0.1700
Data Index: 5256268 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1660. Min Range: -4.1660
Max Act: 4.0722. Min Act: -0.1700
Data Index: 6914915 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1660. Min Range: -4.1660
Max Act: 4.0410. Min Act: -0.1700
Data Index: 8128870 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1660. Min Range: -4.1660
Max Act: 4.0097. Min Act: -0.1700
Data Index: 5572773 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1660. Min Range: -4.1660
Max Act: 4.0410. Min Act: -0.1700
Data Index: 8040189 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1660. Min Range: -4.1660
Max Act: 4.0097. Min Act: -0.1700
Data Index: 2096777 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1660. Min Range: -4.1660
Max Act: 3.9785. Min Act: -0.1700
Data Index: 1068839 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1660. Min Range: -4.1660
Max Act: 3.9472. Min Act: -0.1700
Data Index: 1674247 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1660. Min Range: -4.1660
Max Act: 3.9785. Min Act: -0.1700
Data Index: 6661939 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1660. Min Range: -4.1660
Max Act: 3.9785. Min Act: -0.1700
Data Index: 8276104 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1660. Min Range: -4.1660
Max Act: 3.9785. Min Act: -0.1700
Data Index: 2392961 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1660. Min Range: -4.1660
Max Act: 3.9785. Min Act: -0.1700
Data Index: 1699290 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1660. Min Range: -4.1660
Max Act: 3.9785. Min Act: -0.1700
Data Index: 6909554 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1660. Min Range: -4.1660
Max Act: 3.9785. Min Act: -0.1700
Data Index: 823747 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1660. Min Range: -4.1660
Max Act: 3.9472. Min Act: -0.1700
Data Index: 7009449 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1660. Min Range: -4.1660
Max Act: 3.9472. Min Act: -0.1700
Data Index: 7706934 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1660. Min Range: -4.1660
Max Act: 3.9472. Min Act: -0.1700
Data Index: 1272115 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1660. Min Range: -4.1660
Max Act: 3.9159. Min Act: -0.1700
Data Index: 2707666 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #19