Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4011 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3285. Min Range: -4.3285
Max Act: 4.3285. Min Act: -0.1700
Data Index: 3207572 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3285. Min Range: -4.3285
Max Act: 4.2972. Min Act: -0.1700
Data Index: 3806588 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3285. Min Range: -4.3285
Max Act: 4.2347. Min Act: -0.1700
Data Index: 7807898 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3285. Min Range: -4.3285
Max Act: 4.2035. Min Act: -0.1700
Data Index: 132777 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3285. Min Range: -4.3285
Max Act: 4.1722. Min Act: -0.1700
Data Index: 3627460 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3285. Min Range: -4.3285
Max Act: 4.1722. Min Act: -0.1700
Data Index: 4526146 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3285. Min Range: -4.3285
Max Act: 4.1722. Min Act: -0.1700
Data Index: 8257648 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3285. Min Range: -4.3285
Max Act: 4.1722. Min Act: -0.1700
Data Index: 2017514 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3285. Min Range: -4.3285
Max Act: 4.1410. Min Act: -0.1700
Data Index: 7903586 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3285. Min Range: -4.3285
Max Act: 4.1097. Min Act: -0.1700
Data Index: 2309721 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3285. Min Range: -4.3285
Max Act: 4.1097. Min Act: -0.1700
Data Index: 6932753 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3285. Min Range: -4.3285
Max Act: 4.1097. Min Act: -0.1700
Data Index: 7165746 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3285. Min Range: -4.3285
Max Act: 4.1097. Min Act: -0.1700
Data Index: 1383205 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3285. Min Range: -4.3285
Max Act: 4.1097. Min Act: -0.1700
Data Index: 866763 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3285. Min Range: -4.3285
Max Act: 4.1097. Min Act: -0.1700
Data Index: 5962599 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3285. Min Range: -4.3285
Max Act: 4.1097. Min Act: -0.1700
Data Index: 4731269 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3285. Min Range: -4.3285
Max Act: 4.0472. Min Act: -0.1700
Data Index: 1167013 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3285. Min Range: -4.3285
Max Act: 4.0785. Min Act: -0.1700
Data Index: 1766255 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3285. Min Range: -4.3285
Max Act: 4.0785. Min Act: -0.1700
Data Index: 4392318 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3285. Min Range: -4.3285
Max Act: 4.0785. Min Act: -0.1700
Data Index: 7450328 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #19