Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4097 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7330. Min Range: -8.7330
Max Act: 8.7330. Min Act: -0.1700
Data Index: 5333144 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7330. Min Range: -8.7330
Max Act: 8.7330. Min Act: -0.1700
Data Index: 6599841 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7330. Min Range: -8.7330
Max Act: 8.6705. Min Act: -0.1700
Data Index: 5194594 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7330. Min Range: -8.7330
Max Act: 8.5455. Min Act: -0.1700
Data Index: 5080720 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7330. Min Range: -8.7330
Max Act: 8.4830. Min Act: -0.1700
Data Index: 3557195 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7330. Min Range: -8.7330
Max Act: 8.4830. Min Act: -0.1700
Data Index: 1838658 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7330. Min Range: -8.7330
Max Act: 8.3580. Min Act: -0.1700
Data Index: 1231317 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7330. Min Range: -8.7330
Max Act: 8.3580. Min Act: -0.1700
Data Index: 1268660 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7330. Min Range: -8.7330
Max Act: 8.2955. Min Act: -0.1700
Data Index: 4692560 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7330. Min Range: -8.7330
Max Act: 8.2955. Min Act: -0.1700
Data Index: 8221507 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7330. Min Range: -8.7330
Max Act: 8.2955. Min Act: -0.1700
Data Index: 2573782 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7330. Min Range: -8.7330
Max Act: 8.2330. Min Act: -0.1700
Data Index: 4082091 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7330. Min Range: -8.7330
Max Act: 8.2330. Min Act: -0.1700
Data Index: 244473 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7330. Min Range: -8.7330
Max Act: 8.2330. Min Act: -0.1700
Data Index: 2766444 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7330. Min Range: -8.7330
Max Act: 8.1705. Min Act: -0.1700
Data Index: 7153171 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7330. Min Range: -8.7330
Max Act: 8.1705. Min Act: -0.1700
Data Index: 6659817 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7330. Min Range: -8.7330
Max Act: 8.1080. Min Act: -0.1700
Data Index: 6361332 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7330. Min Range: -8.7330
Max Act: 8.0455. Min Act: -0.1700
Data Index: 5305855 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7330. Min Range: -8.7330
Max Act: 8.0455. Min Act: -0.1700
Data Index: 2758596 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7330. Min Range: -8.7330
Max Act: 8.0455. Min Act: -0.1700
Data Index: 4974914 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #19