Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2979 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8058. Min Range: -7.8058
Max Act: 7.8058. Min Act: -0.1700
Data Index: 4177546 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8058. Min Range: -7.8058
Max Act: 7.6808. Min Act: -0.1700
Data Index: 1442329 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8058. Min Range: -7.8058
Max Act: 7.6183. Min Act: -0.1700
Data Index: 4363869 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8058. Min Range: -7.8058
Max Act: 7.5245. Min Act: -0.1700
Data Index: 3144419 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8058. Min Range: -7.8058
Max Act: 7.4620. Min Act: -0.1700
Data Index: 6610328 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8058. Min Range: -7.8058
Max Act: 7.3995. Min Act: -0.1700
Data Index: 1660556 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8058. Min Range: -7.8058
Max Act: 7.3683. Min Act: -0.1700
Data Index: 6068378 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8058. Min Range: -7.8058
Max Act: 7.3683. Min Act: -0.1700
Data Index: 273494 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8058. Min Range: -7.8058
Max Act: 7.3370. Min Act: -0.1700
Data Index: 1146037 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8058. Min Range: -7.8058
Max Act: 7.3370. Min Act: -0.1700
Data Index: 4606234 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8058. Min Range: -7.8058
Max Act: 7.3058. Min Act: -0.1700
Data Index: 8588407 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8058. Min Range: -7.8058
Max Act: 7.2745. Min Act: -0.1700
Data Index: 201677 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8058. Min Range: -7.8058
Max Act: 7.2745. Min Act: -0.1700
Data Index: 1893122 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8058. Min Range: -7.8058
Max Act: 7.2745. Min Act: -0.1700
Data Index: 5212433 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8058. Min Range: -7.8058
Max Act: 7.2745. Min Act: -0.1700
Data Index: 7714602 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8058. Min Range: -7.8058
Max Act: 7.2120. Min Act: -0.1700
Data Index: 7556209 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8058. Min Range: -7.8058
Max Act: 7.2120. Min Act: -0.1700
Data Index: 1216692 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8058. Min Range: -7.8058
Max Act: 7.1808. Min Act: -0.1700
Data Index: 7394442 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8058. Min Range: -7.8058
Max Act: 7.1808. Min Act: -0.1700
Data Index: 4723654 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8058. Min Range: -7.8058
Max Act: 7.1808. Min Act: -0.1700
Data Index: 3707432 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #19