Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3395 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3056. Min Range: -5.3056
Max Act: 5.3056. Min Act: -0.1700
Data Index: 7050162 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3056. Min Range: -5.3056
Max Act: 5.1806. Min Act: -0.1700
Data Index: 5108471 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3056. Min Range: -5.3056
Max Act: 5.1806. Min Act: -0.1700
Data Index: 954037 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3056. Min Range: -5.3056
Max Act: 5.1806. Min Act: -0.1700
Data Index: 5537820 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3056. Min Range: -5.3056
Max Act: 5.0868. Min Act: -0.1700
Data Index: 1353034 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3056. Min Range: -5.3056
Max Act: 5.0868. Min Act: -0.1700
Data Index: 5718343 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3056. Min Range: -5.3056
Max Act: 5.0556. Min Act: -0.1700
Data Index: 985493 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3056. Min Range: -5.3056
Max Act: 5.0556. Min Act: -0.1700
Data Index: 3617220 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3056. Min Range: -5.3056
Max Act: 5.0556. Min Act: -0.1700
Data Index: 4080185 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3056. Min Range: -5.3056
Max Act: 5.0243. Min Act: -0.1700
Data Index: 4171639 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3056. Min Range: -5.3056
Max Act: 5.0243. Min Act: -0.1700
Data Index: 2481006 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3056. Min Range: -5.3056
Max Act: 5.0243. Min Act: -0.1700
Data Index: 881044 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3056. Min Range: -5.3056
Max Act: 5.0556. Min Act: -0.1700
Data Index: 1387490 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3056. Min Range: -5.3056
Max Act: 5.0243. Min Act: -0.1700
Data Index: 5405464 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3056. Min Range: -5.3056
Max Act: 4.9618. Min Act: -0.1700
Data Index: 184155 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3056. Min Range: -5.3056
Max Act: 4.9931. Min Act: -0.1700
Data Index: 5627327 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3056. Min Range: -5.3056
Max Act: 4.9931. Min Act: -0.1700
Data Index: 3884121 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3056. Min Range: -5.3056
Max Act: 4.9931. Min Act: -0.1700
Data Index: 6906340 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3056. Min Range: -5.3056
Max Act: 4.9931. Min Act: -0.1700
Data Index: 3213506 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3056. Min Range: -5.3056
Max Act: 4.9931. Min Act: -0.1700
Data Index: 5522219 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #19