Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5495 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9883. Min Range: -5.9883
Max Act: 5.9883. Min Act: -0.1700
Data Index: 4625362 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9883. Min Range: -5.9883
Max Act: 5.9258. Min Act: -0.1700
Data Index: 5992492 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9883. Min Range: -5.9883
Max Act: 5.8945. Min Act: -0.1700
Data Index: 7794144 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9883. Min Range: -5.9883
Max Act: 5.8633. Min Act: -0.1700
Data Index: 6911874 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9883. Min Range: -5.9883
Max Act: 5.8320. Min Act: -0.1699
Data Index: 4971227 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9883. Min Range: -5.9883
Max Act: 5.8320. Min Act: -0.1700
Data Index: 8211554 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9883. Min Range: -5.9883
Max Act: 5.7695. Min Act: -0.1700
Data Index: 2216301 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9883. Min Range: -5.9883
Max Act: 5.7383. Min Act: -0.1700
Data Index: 8717895 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9883. Min Range: -5.9883
Max Act: 5.7383. Min Act: -0.1700
Data Index: 759826 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9883. Min Range: -5.9883
Max Act: 5.7070. Min Act: -0.1700
Data Index: 7857161 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9883. Min Range: -5.9883
Max Act: 5.7070. Min Act: -0.1700
Data Index: 3449250 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9883. Min Range: -5.9883
Max Act: 5.6758. Min Act: -0.1700
Data Index: 6494485 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9883. Min Range: -5.9883
Max Act: 5.7070. Min Act: -0.1700
Data Index: 6746690 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9883. Min Range: -5.9883
Max Act: 5.6758. Min Act: -0.1700
Data Index: 429728 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9883. Min Range: -5.9883
Max Act: 5.6758. Min Act: -0.1700
Data Index: 3006064 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9883. Min Range: -5.9883
Max Act: 5.6758. Min Act: -0.1700
Data Index: 1955484 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9883. Min Range: -5.9883
Max Act: 5.6445. Min Act: -0.1700
Data Index: 7615303 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9883. Min Range: -5.9883
Max Act: 5.6133. Min Act: -0.1700
Data Index: 3674676 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9883. Min Range: -5.9883
Max Act: 5.5508. Min Act: -0.1699
Data Index: 4651034 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9883. Min Range: -5.9883
Max Act: 5.4883. Min Act: -0.1700
Data Index: 2836010 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #19