Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4431 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.8122. Min Range: -3.8122
Max Act: 3.8122. Min Act: -0.1700
Data Index: 4614023 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8122. Min Range: -3.8122
Max Act: 3.7184. Min Act: -0.1700
Data Index: 6052203 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8122. Min Range: -3.8122
Max Act: 3.7027. Min Act: -0.1700
Data Index: 2732589 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8122. Min Range: -3.8122
Max Act: 3.5462. Min Act: -0.1700
Data Index: 3859858 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8122. Min Range: -3.8122
Max Act: 3.4523. Min Act: -0.1700
Data Index: 1359145 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8122. Min Range: -3.8122
Max Act: 3.4679. Min Act: -0.1700
Data Index: 8211026 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8122. Min Range: -3.8122
Max Act: 3.4523. Min Act: -0.1700
Data Index: 220504 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8122. Min Range: -3.8122
Max Act: 3.4523. Min Act: -0.1700
Data Index: 7622818 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8122. Min Range: -3.8122
Max Act: 3.4523. Min Act: -0.1700
Data Index: 8695155 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8122. Min Range: -3.8122
Max Act: 3.4366. Min Act: -0.1700
Data Index: 6448855 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8122. Min Range: -3.8122
Max Act: 3.4366. Min Act: -0.1700
Data Index: 5883765 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8122. Min Range: -3.8122
Max Act: 3.4209. Min Act: -0.1700
Data Index: 3511730 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8122. Min Range: -3.8122
Max Act: 3.4209. Min Act: -0.1700
Data Index: 4786347 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8122. Min Range: -3.8122
Max Act: 3.4209. Min Act: -0.1700
Data Index: 3533225 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8122. Min Range: -3.8122
Max Act: 3.3896. Min Act: -0.1700
Data Index: 7570517 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8122. Min Range: -3.8122
Max Act: 3.4052. Min Act: -0.1700
Data Index: 7999514 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8122. Min Range: -3.8122
Max Act: 3.3739. Min Act: -0.1700
Data Index: 655440 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8122. Min Range: -3.8122
Max Act: 3.3739. Min Act: -0.1700
Data Index: 2116047 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8122. Min Range: -3.8122
Max Act: 3.3739. Min Act: -0.1700
Data Index: 7896006 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8122. Min Range: -3.8122
Max Act: 3.3896. Min Act: -0.1700
Data Index: 8654187 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #19