Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3468 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9995. Min Range: -4.9995
Max Act: 4.9995. Min Act: -0.1700
Data Index: 6747377 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9995. Min Range: -4.9995
Max Act: 4.3432. Min Act: -0.1700
Data Index: 3565331 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9995. Min Range: -4.9995
Max Act: 4.3120. Min Act: -0.1700
Data Index: 7750804 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9995. Min Range: -4.9995
Max Act: 4.2495. Min Act: -0.1700
Data Index: 8706730 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9995. Min Range: -4.9995
Max Act: 4.1245. Min Act: -0.1700
Data Index: 7838455 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9995. Min Range: -4.9995
Max Act: 4.0619. Min Act: -0.1700
Data Index: 2619540 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9995. Min Range: -4.9995
Max Act: 4.0619. Min Act: -0.1700
Data Index: 3235998 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9995. Min Range: -4.9995
Max Act: 4.0619. Min Act: -0.1700
Data Index: 2471669 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9995. Min Range: -4.9995
Max Act: 4.0307. Min Act: -0.1700
Data Index: 6129539 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9995. Min Range: -4.9995
Max Act: 3.9682. Min Act: -0.1700
Data Index: 6329651 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9995. Min Range: -4.9995
Max Act: 3.9056. Min Act: -0.1700
Data Index: 1819864 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9995. Min Range: -4.9995
Max Act: 3.9056. Min Act: -0.1700
Data Index: 390870 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9995. Min Range: -4.9995
Max Act: 3.8744. Min Act: -0.1700
Data Index: 5800920 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9995. Min Range: -4.9995
Max Act: 3.9056. Min Act: -0.1700
Data Index: 6945292 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9995. Min Range: -4.9995
Max Act: 3.8744. Min Act: -0.1700
Data Index: 6352317 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9995. Min Range: -4.9995
Max Act: 3.8744. Min Act: -0.1700
Data Index: 5708337 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9995. Min Range: -4.9995
Max Act: 3.8744. Min Act: -0.1700
Data Index: 3271103 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9995. Min Range: -4.9995
Max Act: 3.8744. Min Act: -0.1700
Data Index: 4077432 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9995. Min Range: -4.9995
Max Act: 3.8431. Min Act: -0.1700
Data Index: 2431488 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9995. Min Range: -4.9995
Max Act: 3.8744. Min Act: -0.1700
Data Index: 3659825 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #19