Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 966 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9962. Min Range: -7.9962
Max Act: 7.9962. Min Act: -0.1700
Data Index: 8140176 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9962. Min Range: -7.9962
Max Act: 7.8712. Min Act: -0.1700
Data Index: 3268111 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9962. Min Range: -7.9962
Max Act: 7.7149. Min Act: -0.1700
Data Index: 8147257 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9962. Min Range: -7.9962
Max Act: 7.6837. Min Act: -0.1700
Data Index: 2337937 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9962. Min Range: -7.9962
Max Act: 7.5274. Min Act: -0.1700
Data Index: 3293230 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9962. Min Range: -7.9962
Max Act: 7.4337. Min Act: -0.1700
Data Index: 2836397 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9962. Min Range: -7.9962
Max Act: 7.4024. Min Act: -0.1700
Data Index: 5345291 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9962. Min Range: -7.9962
Max Act: 7.4024. Min Act: -0.1700
Data Index: 3249573 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9962. Min Range: -7.9962
Max Act: 7.3712. Min Act: -0.1700
Data Index: 24981 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9962. Min Range: -7.9962
Max Act: 7.3087. Min Act: -0.1700
Data Index: 6427634 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9962. Min Range: -7.9962
Max Act: 7.3087. Min Act: -0.1700
Data Index: 7411011 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9962. Min Range: -7.9962
Max Act: 7.3087. Min Act: -0.1700
Data Index: 3489070 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9962. Min Range: -7.9962
Max Act: 7.2774. Min Act: -0.1700
Data Index: 1858828 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9962. Min Range: -7.9962
Max Act: 7.2462. Min Act: -0.1700
Data Index: 7565772 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9962. Min Range: -7.9962
Max Act: 7.2462. Min Act: -0.1700
Data Index: 4828725 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9962. Min Range: -7.9962
Max Act: 7.2462. Min Act: -0.1700
Data Index: 920155 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9962. Min Range: -7.9962
Max Act: 7.2462. Min Act: -0.1700
Data Index: 7839735 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9962. Min Range: -7.9962
Max Act: 7.2149. Min Act: -0.1700
Data Index: 2327219 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9962. Min Range: -7.9962
Max Act: 7.1524. Min Act: -0.1700
Data Index: 63814 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9962. Min Range: -7.9962
Max Act: 7.1212. Min Act: -0.1700
Data Index: 1855659 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #19