Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 174 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9103. Min Range: -7.9103
Max Act: 7.9103. Min Act: -0.1700
Data Index: 6812807 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9103. Min Range: -7.9103
Max Act: 7.8166. Min Act: -0.1700
Data Index: 5443274 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9103. Min Range: -7.9103
Max Act: 7.7541. Min Act: -0.1700
Data Index: 2390319 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9103. Min Range: -7.9103
Max Act: 7.6916. Min Act: -0.1700
Data Index: 7344232 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9103. Min Range: -7.9103
Max Act: 7.5978. Min Act: -0.1700
Data Index: 3999156 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9103. Min Range: -7.9103
Max Act: 7.5353. Min Act: -0.1700
Data Index: 7344227 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9103. Min Range: -7.9103
Max Act: 7.5353. Min Act: -0.1700
Data Index: 1846346 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9103. Min Range: -7.9103
Max Act: 7.4416. Min Act: -0.1700
Data Index: 4984129 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9103. Min Range: -7.9103
Max Act: 7.4728. Min Act: -0.1700
Data Index: 1410780 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9103. Min Range: -7.9103
Max Act: 7.4416. Min Act: -0.1700
Data Index: 5993991 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9103. Min Range: -7.9103
Max Act: 7.4416. Min Act: -0.1700
Data Index: 4385 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9103. Min Range: -7.9103
Max Act: 7.3166. Min Act: -0.1700
Data Index: 2609623 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9103. Min Range: -7.9103
Max Act: 7.3478. Min Act: -0.1700
Data Index: 8645753 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9103. Min Range: -7.9103
Max Act: 7.3166. Min Act: -0.1700
Data Index: 361616 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9103. Min Range: -7.9103
Max Act: 7.3166. Min Act: -0.1700
Data Index: 2238430 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9103. Min Range: -7.9103
Max Act: 7.2853. Min Act: -0.1700
Data Index: 5994467 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9103. Min Range: -7.9103
Max Act: 7.2853. Min Act: -0.1700
Data Index: 7211981 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9103. Min Range: -7.9103
Max Act: 7.2853. Min Act: -0.1700
Data Index: 4543423 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9103. Min Range: -7.9103
Max Act: 7.2541. Min Act: -0.1700
Data Index: 8080886 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9103. Min Range: -7.9103
Max Act: 7.2228. Min Act: -0.1700
Data Index: 7614750 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #19