Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5322 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1055. Min Range: -7.1055
Max Act: 7.1055. Min Act: -0.1700
Data Index: 599930 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1055. Min Range: -7.1055
Max Act: 7.0430. Min Act: -0.1700
Data Index: 2795661 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1055. Min Range: -7.1055
Max Act: 6.9493. Min Act: -0.1700
Data Index: 4797862 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1055. Min Range: -7.1055
Max Act: 6.8868. Min Act: -0.1700
Data Index: 3216579 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1055. Min Range: -7.1055
Max Act: 6.8243. Min Act: -0.1700
Data Index: 4634285 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1055. Min Range: -7.1055
Max Act: 6.7305. Min Act: -0.1700
Data Index: 7109798 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1055. Min Range: -7.1055
Max Act: 6.7305. Min Act: -0.1700
Data Index: 2737215 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1055. Min Range: -7.1055
Max Act: 6.6680. Min Act: -0.1700
Data Index: 270010 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1055. Min Range: -7.1055
Max Act: 6.7305. Min Act: -0.1700
Data Index: 306133 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1055. Min Range: -7.1055
Max Act: 6.6680. Min Act: -0.1700
Data Index: 8706882 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1055. Min Range: -7.1055
Max Act: 6.6055. Min Act: -0.1700
Data Index: 6980714 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1055. Min Range: -7.1055
Max Act: 6.5743. Min Act: -0.1700
Data Index: 7851885 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1055. Min Range: -7.1055
Max Act: 6.5118. Min Act: -0.1700
Data Index: 4397639 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1055. Min Range: -7.1055
Max Act: 6.5118. Min Act: -0.1700
Data Index: 90150 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1055. Min Range: -7.1055
Max Act: 6.5118. Min Act: -0.1700
Data Index: 3353206 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1055. Min Range: -7.1055
Max Act: 6.4493. Min Act: -0.1700
Data Index: 5856544 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1055. Min Range: -7.1055
Max Act: 6.4493. Min Act: -0.1700
Data Index: 8491183 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1055. Min Range: -7.1055
Max Act: 6.4180. Min Act: -0.1700
Data Index: 4157521 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1055. Min Range: -7.1055
Max Act: 6.3868. Min Act: -0.1700
Data Index: 5060461 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1055. Min Range: -7.1055
Max Act: 6.3868. Min Act: -0.1700
Data Index: 281812 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #19