Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1076 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2181. Min Range: -7.2181
Max Act: 7.2181. Min Act: -0.1700
Data Index: 1276803 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2181. Min Range: -7.2181
Max Act: 7.2181. Min Act: -0.1700
Data Index: 7767370 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2181. Min Range: -7.2181
Max Act: 7.2181. Min Act: -0.1699
Data Index: 5142109 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2181. Min Range: -7.2181
Max Act: 7.1869. Min Act: -0.1700
Data Index: 4067932 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2181. Min Range: -7.2181
Max Act: 7.1869. Min Act: -0.1700
Data Index: 6362443 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2181. Min Range: -7.2181
Max Act: 7.1244. Min Act: -0.1700
Data Index: 7526408 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2181. Min Range: -7.2181
Max Act: 7.0931. Min Act: -0.1700
Data Index: 627397 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2181. Min Range: -7.2181
Max Act: 7.0931. Min Act: -0.1700
Data Index: 847658 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2181. Min Range: -7.2181
Max Act: 7.0931. Min Act: -0.1700
Data Index: 8070747 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2181. Min Range: -7.2181
Max Act: 7.0931. Min Act: -0.1700
Data Index: 5806566 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2181. Min Range: -7.2181
Max Act: 7.0619. Min Act: -0.1700
Data Index: 8377677 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2181. Min Range: -7.2181
Max Act: 7.0306. Min Act: -0.1700
Data Index: 3072707 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2181. Min Range: -7.2181
Max Act: 6.9994. Min Act: -0.1700
Data Index: 5673648 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2181. Min Range: -7.2181
Max Act: 7.0306. Min Act: -0.1700
Data Index: 3680016 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2181. Min Range: -7.2181
Max Act: 6.9994. Min Act: -0.1700
Data Index: 6075857 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2181. Min Range: -7.2181
Max Act: 6.9681. Min Act: -0.1700
Data Index: 4182024 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2181. Min Range: -7.2181
Max Act: 6.9994. Min Act: -0.1700
Data Index: 2838122 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2181. Min Range: -7.2181
Max Act: 6.9681. Min Act: -0.1700
Data Index: 4182025 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2181. Min Range: -7.2181
Max Act: 6.9681. Min Act: -0.1700
Data Index: 5872825 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2181. Min Range: -7.2181
Max Act: 6.9681. Min Act: -0.1700
Data Index: 4785200 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #19