Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2853 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.8155. Min Range: -2.8155
Max Act: 2.8155. Min Act: -0.1700
Data Index: 1510315 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8155. Min Range: -2.8155
Max Act: 2.7836. Min Act: -0.1700
Data Index: 6356950 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8155. Min Range: -2.8155
Max Act: 2.7517. Min Act: -0.1700
Data Index: 7626715 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8155. Min Range: -2.8155
Max Act: 2.7517. Min Act: -0.1700
Data Index: 7987340 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8155. Min Range: -2.8155
Max Act: 2.7517. Min Act: -0.1700
Data Index: 2187141 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8155. Min Range: -2.8155
Max Act: 2.7357. Min Act: -0.1700
Data Index: 4773440 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8155. Min Range: -2.8155
Max Act: 2.7357. Min Act: -0.1700
Data Index: 1701537 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8155. Min Range: -2.8155
Max Act: 2.7198. Min Act: -0.1700
Data Index: 243012 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8155. Min Range: -2.8155
Max Act: 2.7038. Min Act: -0.1700
Data Index: 2643554 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8155. Min Range: -2.8155
Max Act: 2.6878. Min Act: -0.1700
Data Index: 5276131 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8155. Min Range: -2.8155
Max Act: 2.6717. Min Act: -0.1700
Data Index: 3934006 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8155. Min Range: -2.8155
Max Act: 2.6717. Min Act: -0.1700
Data Index: 7626726 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8155. Min Range: -2.8155
Max Act: 2.6557. Min Act: -0.1700
Data Index: 1871776 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8155. Min Range: -2.8155
Max Act: 2.6397. Min Act: -0.1700
Data Index: 6272888 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8155. Min Range: -2.8155
Max Act: 2.6557. Min Act: -0.1700
Data Index: 1379919 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8155. Min Range: -2.8155
Max Act: 2.6236. Min Act: -0.1700
Data Index: 7873296 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8155. Min Range: -2.8155
Max Act: 2.6397. Min Act: -0.1700
Data Index: 1136496 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8155. Min Range: -2.8155
Max Act: 2.6075. Min Act: -0.1700
Data Index: 5691444 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8155. Min Range: -2.8155
Max Act: 2.6236. Min Act: -0.1700
Data Index: 3939448 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8155. Min Range: -2.8155
Max Act: 2.6075. Min Act: -0.1699
Data Index: 1558272 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #19