Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3499 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0445. Min Range: -8.0445
Max Act: 8.0445. Min Act: -0.1700
Data Index: 883311 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0445. Min Range: -8.0445
Max Act: 7.5758. Min Act: -0.1700
Data Index: 4032761 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0445. Min Range: -8.0445
Max Act: 7.3883. Min Act: -0.1700
Data Index: 1979459 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0445. Min Range: -8.0445
Max Act: 7.2945. Min Act: -0.1700
Data Index: 4660766 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0445. Min Range: -8.0445
Max Act: 7.1695. Min Act: -0.1700
Data Index: 8245537 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0445. Min Range: -8.0445
Max Act: 7.2008. Min Act: -0.1700
Data Index: 1872859 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0445. Min Range: -8.0445
Max Act: 7.1070. Min Act: -0.1700
Data Index: 2511892 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0445. Min Range: -8.0445
Max Act: 7.1070. Min Act: -0.1700
Data Index: 7692512 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0445. Min Range: -8.0445
Max Act: 7.0758. Min Act: -0.1700
Data Index: 8147389 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0445. Min Range: -8.0445
Max Act: 7.0445. Min Act: -0.1700
Data Index: 2725308 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0445. Min Range: -8.0445
Max Act: 7.0445. Min Act: -0.1700
Data Index: 8110293 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0445. Min Range: -8.0445
Max Act: 7.0133. Min Act: -0.1700
Data Index: 4700940 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0445. Min Range: -8.0445
Max Act: 6.9820. Min Act: -0.1700
Data Index: 1907606 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0445. Min Range: -8.0445
Max Act: 6.9820. Min Act: -0.1700
Data Index: 8062406 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0445. Min Range: -8.0445
Max Act: 6.9820. Min Act: -0.1700
Data Index: 7445085 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0445. Min Range: -8.0445
Max Act: 6.9508. Min Act: -0.1700
Data Index: 8681581 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0445. Min Range: -8.0445
Max Act: 6.9508. Min Act: -0.1700
Data Index: 5609980 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0445. Min Range: -8.0445
Max Act: 6.9195. Min Act: -0.1700
Data Index: 6088466 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0445. Min Range: -8.0445
Max Act: 6.9195. Min Act: -0.1700
Data Index: 6557659 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0445. Min Range: -8.0445
Max Act: 6.9508. Min Act: -0.1700
Data Index: 3633802 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #19