Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2023 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.5247. Min Range: -4.5247
Max Act: 4.4622. Min Act: -0.1700
Data Index: 7797902 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5247. Min Range: -4.5247
Max Act: 4.5247. Min Act: -0.1700
Data Index: 5834753 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5247. Min Range: -4.5247
Max Act: 4.4622. Min Act: -0.1700
Data Index: 1358168 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5247. Min Range: -4.5247
Max Act: 4.4309. Min Act: -0.1700
Data Index: 1746967 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5247. Min Range: -4.5247
Max Act: 4.4309. Min Act: -0.1700
Data Index: 4405581 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5247. Min Range: -4.5247
Max Act: 4.3997. Min Act: -0.1700
Data Index: 5073379 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5247. Min Range: -4.5247
Max Act: 4.3997. Min Act: -0.1700
Data Index: 1914104 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5247. Min Range: -4.5247
Max Act: 4.3684. Min Act: -0.1700
Data Index: 5609697 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5247. Min Range: -4.5247
Max Act: 4.3684. Min Act: -0.1700
Data Index: 2997901 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5247. Min Range: -4.5247
Max Act: 4.3372. Min Act: -0.1700
Data Index: 5073380 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5247. Min Range: -4.5247
Max Act: 4.3059. Min Act: -0.1700
Data Index: 2486646 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5247. Min Range: -4.5247
Max Act: 4.3372. Min Act: -0.1700
Data Index: 1008269 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5247. Min Range: -4.5247
Max Act: 4.3059. Min Act: -0.1700
Data Index: 1751508 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5247. Min Range: -4.5247
Max Act: 4.3059. Min Act: -0.1700
Data Index: 246357 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5247. Min Range: -4.5247
Max Act: 4.3059. Min Act: -0.1700
Data Index: 403304 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5247. Min Range: -4.5247
Max Act: 4.2434. Min Act: -0.1700
Data Index: 137481 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5247. Min Range: -4.5247
Max Act: 4.2747. Min Act: -0.1700
Data Index: 241795 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5247. Min Range: -4.5247
Max Act: 4.2747. Min Act: -0.1700
Data Index: 3778867 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5247. Min Range: -4.5247
Max Act: 4.2122. Min Act: -0.1700
Data Index: 3935045 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5247. Min Range: -4.5247
Max Act: 4.2434. Min Act: -0.1700
Data Index: 4111104 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #19