Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3481 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7266. Min Range: -5.7266
Max Act: 5.7266. Min Act: -0.1700
Data Index: 1496803 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7266. Min Range: -5.7266
Max Act: 5.6954. Min Act: -0.1700
Data Index: 512730 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7266. Min Range: -5.7266
Max Act: 5.7266. Min Act: -0.1700
Data Index: 755355 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7266. Min Range: -5.7266
Max Act: 5.6954. Min Act: -0.1700
Data Index: 7943579 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7266. Min Range: -5.7266
Max Act: 5.6954. Min Act: -0.1700
Data Index: 6529273 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7266. Min Range: -5.7266
Max Act: 5.6329. Min Act: -0.1700
Data Index: 7452291 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7266. Min Range: -5.7266
Max Act: 5.6641. Min Act: -0.1700
Data Index: 8485546 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7266. Min Range: -5.7266
Max Act: 5.6641. Min Act: -0.1700
Data Index: 591439 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7266. Min Range: -5.7266
Max Act: 5.6641. Min Act: -0.1700
Data Index: 5238290 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7266. Min Range: -5.7266
Max Act: 5.6641. Min Act: -0.1700
Data Index: 179188 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7266. Min Range: -5.7266
Max Act: 5.6641. Min Act: -0.1700
Data Index: 6119201 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7266. Min Range: -5.7266
Max Act: 5.6641. Min Act: -0.1700
Data Index: 385772 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7266. Min Range: -5.7266
Max Act: 5.6641. Min Act: -0.1700
Data Index: 6480507 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7266. Min Range: -5.7266
Max Act: 5.6329. Min Act: -0.1700
Data Index: 4511375 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7266. Min Range: -5.7266
Max Act: 5.6329. Min Act: -0.1700
Data Index: 2301755 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7266. Min Range: -5.7266
Max Act: 5.6329. Min Act: -0.1700
Data Index: 5019920 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7266. Min Range: -5.7266
Max Act: 5.6329. Min Act: -0.1700
Data Index: 2542687 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7266. Min Range: -5.7266
Max Act: 5.6329. Min Act: -0.1700
Data Index: 1436295 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7266. Min Range: -5.7266
Max Act: 5.6329. Min Act: -0.1700
Data Index: 3622089 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7266. Min Range: -5.7266
Max Act: 5.6329. Min Act: -0.1700
Data Index: 6285319 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #19