Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4625 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5958. Min Range: -7.5958
Max Act: 7.5958. Min Act: -0.1700
Data Index: 7193654 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5958. Min Range: -7.5958
Max Act: 7.5333. Min Act: -0.1700
Data Index: 6188711 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5958. Min Range: -7.5958
Max Act: 7.4708. Min Act: -0.1700
Data Index: 6515135 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5958. Min Range: -7.5958
Max Act: 7.2208. Min Act: -0.1685
Data Index: 8210361 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5958. Min Range: -7.5958
Max Act: 7.1895. Min Act: -0.1700
Data Index: 5043354 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5958. Min Range: -7.5958
Max Act: 7.1583. Min Act: -0.1700
Data Index: 1071975 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5958. Min Range: -7.5958
Max Act: 7.2208. Min Act: -0.1699
Data Index: 8531396 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5958. Min Range: -7.5958
Max Act: 7.0958. Min Act: -0.1700
Data Index: 7230679 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5958. Min Range: -7.5958
Max Act: 7.0333. Min Act: -0.1700
Data Index: 2050996 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5958. Min Range: -7.5958
Max Act: 6.9708. Min Act: -0.1700
Data Index: 3079184 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5958. Min Range: -7.5958
Max Act: 6.9083. Min Act: -0.1700
Data Index: 2861756 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5958. Min Range: -7.5958
Max Act: 6.9395. Min Act: -0.1700
Data Index: 101550 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5958. Min Range: -7.5958
Max Act: 6.9395. Min Act: -0.1699
Data Index: 1827380 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5958. Min Range: -7.5958
Max Act: 6.8458. Min Act: -0.1699
Data Index: 6959788 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5958. Min Range: -7.5958
Max Act: 6.8458. Min Act: -0.1690
Data Index: 6003065 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5958. Min Range: -7.5958
Max Act: 6.8145. Min Act: -0.1699
Data Index: 7102585 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5958. Min Range: -7.5958
Max Act: 6.7833. Min Act: -0.1700
Data Index: 7873076 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5958. Min Range: -7.5958
Max Act: 6.8145. Min Act: -0.1700
Data Index: 1156469 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5958. Min Range: -7.5958
Max Act: 6.8145. Min Act: -0.1700
Data Index: 6260377 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5958. Min Range: -7.5958
Max Act: 6.7833. Min Act: -0.1700
Data Index: 3268016 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #19