Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2962 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8770. Min Range: -7.8770
Max Act: 7.8770. Min Act: -0.1700
Data Index: 5991502 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8770. Min Range: -7.8770
Max Act: 7.7520. Min Act: -0.1700
Data Index: 7556415 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8770. Min Range: -7.8770
Max Act: 7.6895. Min Act: -0.1700
Data Index: 432390 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8770. Min Range: -7.8770
Max Act: 7.6270. Min Act: -0.1700
Data Index: 2785329 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8770. Min Range: -7.8770
Max Act: 7.5958. Min Act: -0.1700
Data Index: 7614276 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8770. Min Range: -7.8770
Max Act: 7.5333. Min Act: -0.1700
Data Index: 8621517 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8770. Min Range: -7.8770
Max Act: 7.5333. Min Act: -0.1700
Data Index: 1342170 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8770. Min Range: -7.8770
Max Act: 7.4708. Min Act: -0.1700
Data Index: 4694318 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8770. Min Range: -7.8770
Max Act: 7.4708. Min Act: -0.1700
Data Index: 1120701 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8770. Min Range: -7.8770
Max Act: 7.4083. Min Act: -0.1700
Data Index: 6813810 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8770. Min Range: -7.8770
Max Act: 7.4395. Min Act: -0.1700
Data Index: 6860479 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8770. Min Range: -7.8770
Max Act: 7.3770. Min Act: -0.1700
Data Index: 2617013 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8770. Min Range: -7.8770
Max Act: 7.3770. Min Act: -0.1700
Data Index: 2207789 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8770. Min Range: -7.8770
Max Act: 7.3458. Min Act: -0.1700
Data Index: 4703611 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8770. Min Range: -7.8770
Max Act: 7.3458. Min Act: -0.1700
Data Index: 8553215 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8770. Min Range: -7.8770
Max Act: 7.3458. Min Act: -0.1700
Data Index: 351160 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8770. Min Range: -7.8770
Max Act: 7.2520. Min Act: -0.1700
Data Index: 7218640 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8770. Min Range: -7.8770
Max Act: 7.2833. Min Act: -0.1700
Data Index: 7849997 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8770. Min Range: -7.8770
Max Act: 7.2208. Min Act: -0.1700
Data Index: 1554925 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8770. Min Range: -7.8770
Max Act: 7.1895. Min Act: -0.1700
Data Index: 8280108 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #19