Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2816 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7082. Min Range: -6.7082
Max Act: 6.7082. Min Act: -0.1700
Data Index: 5269764 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7082. Min Range: -6.7082
Max Act: 6.6457. Min Act: -0.1700
Data Index: 4625340 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7082. Min Range: -6.7082
Max Act: 6.4270. Min Act: -0.1700
Data Index: 688120 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7082. Min Range: -6.7082
Max Act: 6.3332. Min Act: -0.1700
Data Index: 8138786 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7082. Min Range: -6.7082
Max Act: 6.3332. Min Act: -0.1700
Data Index: 233622 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7082. Min Range: -6.7082
Max Act: 6.3645. Min Act: -0.1700
Data Index: 2583318 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7082. Min Range: -6.7082
Max Act: 6.3020. Min Act: -0.1700
Data Index: 821152 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7082. Min Range: -6.7082
Max Act: 6.3020. Min Act: -0.1700
Data Index: 3612746 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7082. Min Range: -6.7082
Max Act: 6.3020. Min Act: -0.1700
Data Index: 2883943 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7082. Min Range: -6.7082
Max Act: 6.2707. Min Act: -0.1700
Data Index: 890408 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7082. Min Range: -6.7082
Max Act: 6.2395. Min Act: -0.1700
Data Index: 1238892 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7082. Min Range: -6.7082
Max Act: 6.2395. Min Act: -0.1700
Data Index: 243158 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7082. Min Range: -6.7082
Max Act: 6.2395. Min Act: -0.1700
Data Index: 1351919 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7082. Min Range: -6.7082
Max Act: 6.2082. Min Act: -0.1700
Data Index: 7217864 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7082. Min Range: -6.7082
Max Act: 6.2082. Min Act: -0.1700
Data Index: 535755 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7082. Min Range: -6.7082
Max Act: 6.2082. Min Act: -0.1700
Data Index: 7425788 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7082. Min Range: -6.7082
Max Act: 6.2082. Min Act: -0.1700
Data Index: 5206703 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7082. Min Range: -6.7082
Max Act: 6.1770. Min Act: -0.1700
Data Index: 3057032 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7082. Min Range: -6.7082
Max Act: 6.1457. Min Act: -0.1700
Data Index: 5390975 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7082. Min Range: -6.7082
Max Act: 6.1770. Min Act: -0.1700
Data Index: 5088352 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #19