Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2946 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3597. Min Range: -7.3597
Max Act: 7.3597. Min Act: -0.1700
Data Index: 4075445 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3597. Min Range: -7.3597
Max Act: 7.1722. Min Act: -0.1700
Data Index: 7845828 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3597. Min Range: -7.3597
Max Act: 7.1722. Min Act: -0.1700
Data Index: 3955340 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3597. Min Range: -7.3597
Max Act: 7.1097. Min Act: -0.1700
Data Index: 6565882 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3597. Min Range: -7.3597
Max Act: 7.0472. Min Act: -0.1700
Data Index: 5781162 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3597. Min Range: -7.3597
Max Act: 7.0785. Min Act: -0.1700
Data Index: 5240177 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3597. Min Range: -7.3597
Max Act: 7.0785. Min Act: -0.1700
Data Index: 6300782 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3597. Min Range: -7.3597
Max Act: 7.0785. Min Act: -0.1700
Data Index: 2753473 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3597. Min Range: -7.3597
Max Act: 7.0472. Min Act: -0.1700
Data Index: 398849 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3597. Min Range: -7.3597
Max Act: 6.9222. Min Act: -0.1700
Data Index: 2414883 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3597. Min Range: -7.3597
Max Act: 6.8910. Min Act: -0.1700
Data Index: 7738209 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3597. Min Range: -7.3597
Max Act: 6.8910. Min Act: -0.1700
Data Index: 5101864 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3597. Min Range: -7.3597
Max Act: 6.8910. Min Act: -0.1700
Data Index: 3941457 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3597. Min Range: -7.3597
Max Act: 6.8597. Min Act: -0.1700
Data Index: 7747085 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3597. Min Range: -7.3597
Max Act: 6.8597. Min Act: -0.1700
Data Index: 7753041 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3597. Min Range: -7.3597
Max Act: 6.8597. Min Act: -0.1700
Data Index: 2984312 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3597. Min Range: -7.3597
Max Act: 6.8597. Min Act: -0.1700
Data Index: 7415209 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3597. Min Range: -7.3597
Max Act: 6.8597. Min Act: -0.1700
Data Index: 6083117 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3597. Min Range: -7.3597
Max Act: 6.8285. Min Act: -0.1700
Data Index: 2608774 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3597. Min Range: -7.3597
Max Act: 6.8285. Min Act: -0.1700
Data Index: 755304 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #19