Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3278 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1927. Min Range: -4.1927
Max Act: 4.1927. Min Act: -0.1700
Data Index: 3562841 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1927. Min Range: -4.1927
Max Act: 4.0990. Min Act: -0.1700
Data Index: 2569946 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1927. Min Range: -4.1927
Max Act: 4.0990. Min Act: -0.1700
Data Index: 2569942 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1927. Min Range: -4.1927
Max Act: 3.9427. Min Act: -0.1700
Data Index: 2419080 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1927. Min Range: -4.1927
Max Act: 3.8489. Min Act: -0.1700
Data Index: 4620996 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1927. Min Range: -4.1927
Max Act: 3.7863. Min Act: -0.1700
Data Index: 4238733 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1927. Min Range: -4.1927
Max Act: 3.8176. Min Act: -0.1700
Data Index: 7215177 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1927. Min Range: -4.1927
Max Act: 3.7863. Min Act: -0.1700
Data Index: 299042 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1927. Min Range: -4.1927
Max Act: 3.7551. Min Act: -0.1700
Data Index: 4620998 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1927. Min Range: -4.1927
Max Act: 3.7863. Min Act: -0.1700
Data Index: 8108085 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1927. Min Range: -4.1927
Max Act: 3.7394. Min Act: -0.1700
Data Index: 6777072 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1927. Min Range: -4.1927
Max Act: 3.7394. Min Act: -0.1700
Data Index: 4620995 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1927. Min Range: -4.1927
Max Act: 3.7238. Min Act: -0.1700
Data Index: 2000589 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1927. Min Range: -4.1927
Max Act: 3.6925. Min Act: -0.1700
Data Index: 6427972 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1927. Min Range: -4.1927
Max Act: 3.7081. Min Act: -0.1700
Data Index: 1358559 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1927. Min Range: -4.1927
Max Act: 3.7081. Min Act: -0.1700
Data Index: 1358558 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1927. Min Range: -4.1927
Max Act: 3.7081. Min Act: -0.1700
Data Index: 6196564 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1927. Min Range: -4.1927
Max Act: 3.6768. Min Act: -0.1700
Data Index: 5340693 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1927. Min Range: -4.1927
Max Act: 3.6925. Min Act: -0.1700
Data Index: 4620997 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1927. Min Range: -4.1927
Max Act: 3.6925. Min Act: -0.1700
Data Index: 5611190 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #19