Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5434 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2766. Min Range: -5.2766
Max Act: 5.2766. Min Act: -0.1700
Data Index: 8039057 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2766. Min Range: -5.2766
Max Act: 5.2766. Min Act: -0.1700
Data Index: 5020252 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2766. Min Range: -5.2766
Max Act: 5.0891. Min Act: -0.1700
Data Index: 5774054 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2766. Min Range: -5.2766
Max Act: 5.0891. Min Act: -0.1700
Data Index: 2131808 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2766. Min Range: -5.2766
Max Act: 5.0579. Min Act: -0.1700
Data Index: 5154317 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2766. Min Range: -5.2766
Max Act: 5.0266. Min Act: -0.1700
Data Index: 47917 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2766. Min Range: -5.2766
Max Act: 5.0266. Min Act: -0.1700
Data Index: 8122404 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2766. Min Range: -5.2766
Max Act: 4.9954. Min Act: -0.1700
Data Index: 1329209 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2766. Min Range: -5.2766
Max Act: 4.9329. Min Act: -0.1700
Data Index: 7076333 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2766. Min Range: -5.2766
Max Act: 4.9329. Min Act: -0.1700
Data Index: 3806116 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2766. Min Range: -5.2766
Max Act: 4.9016. Min Act: -0.1700
Data Index: 5515817 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2766. Min Range: -5.2766
Max Act: 4.8704. Min Act: -0.1700
Data Index: 895522 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2766. Min Range: -5.2766
Max Act: 4.8704. Min Act: -0.1700
Data Index: 8164254 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2766. Min Range: -5.2766
Max Act: 4.8704. Min Act: -0.1700
Data Index: 4885204 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2766. Min Range: -5.2766
Max Act: 4.8704. Min Act: -0.1700
Data Index: 7901449 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2766. Min Range: -5.2766
Max Act: 4.8079. Min Act: -0.1700
Data Index: 3241809 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2766. Min Range: -5.2766
Max Act: 4.8391. Min Act: -0.1700
Data Index: 7882631 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2766. Min Range: -5.2766
Max Act: 4.8391. Min Act: -0.1700
Data Index: 1251290 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2766. Min Range: -5.2766
Max Act: 4.8079. Min Act: -0.1700
Data Index: 1870054 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2766. Min Range: -5.2766
Max Act: 4.8079. Min Act: -0.1700
Data Index: 2750650 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #19