Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1316 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.6613. Min Range: -2.6613
Max Act: 2.6613. Min Act: -0.1700
Data Index: 8411376 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6613. Min Range: -2.6613
Max Act: 2.5971. Min Act: -0.1700
Data Index: 3045967 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6613. Min Range: -2.6613
Max Act: 2.6132. Min Act: -0.1700
Data Index: 7659359 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6613. Min Range: -2.6613
Max Act: 2.5971. Min Act: -0.1700
Data Index: 5834906 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6613. Min Range: -2.6613
Max Act: 2.5971. Min Act: -0.1700
Data Index: 1865239 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6613. Min Range: -2.6613
Max Act: 2.5810. Min Act: -0.1700
Data Index: 7797078 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6613. Min Range: -2.6613
Max Act: 2.5810. Min Act: -0.1700
Data Index: 2970066 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6613. Min Range: -2.6613
Max Act: 2.5648. Min Act: -0.1700
Data Index: 973344 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6613. Min Range: -2.6613
Max Act: 2.5648. Min Act: -0.1700
Data Index: 6985333 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6613. Min Range: -2.6613
Max Act: 2.5325. Min Act: -0.1700
Data Index: 1952371 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6613. Min Range: -2.6613
Max Act: 2.5325. Min Act: -0.1700
Data Index: 8420694 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6613. Min Range: -2.6613
Max Act: 2.5164. Min Act: -0.1700
Data Index: 5198605 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6613. Min Range: -2.6613
Max Act: 2.5002. Min Act: -0.1700
Data Index: 8656294 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6613. Min Range: -2.6613
Max Act: 2.5002. Min Act: -0.1700
Data Index: 8601218 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6613. Min Range: -2.6613
Max Act: 2.5002. Min Act: -0.1700
Data Index: 2575774 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6613. Min Range: -2.6613
Max Act: 2.5164. Min Act: -0.1700
Data Index: 1068857 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6613. Min Range: -2.6613
Max Act: 2.5002. Min Act: -0.1700
Data Index: 3082244 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6613. Min Range: -2.6613
Max Act: 2.5002. Min Act: -0.1700
Data Index: 2425748 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6613. Min Range: -2.6613
Max Act: 2.5164. Min Act: -0.1700
Data Index: 7984156 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6613. Min Range: -2.6613
Max Act: 2.5002. Min Act: -0.1700
Data Index: 4016073 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #19