Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5218 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4601. Min Range: -8.4601
Max Act: 8.4601. Min Act: -0.1700
Data Index: 803602 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4601. Min Range: -8.4601
Max Act: 8.3976. Min Act: -0.1700
Data Index: 8353172 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4601. Min Range: -8.4601
Max Act: 8.3976. Min Act: -0.1700
Data Index: 4688624 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4601. Min Range: -8.4601
Max Act: 8.3351. Min Act: -0.1700
Data Index: 4677440 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4601. Min Range: -8.4601
Max Act: 8.3976. Min Act: -0.1700
Data Index: 5010932 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4601. Min Range: -8.4601
Max Act: 8.2726. Min Act: -0.1700
Data Index: 4227142 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4601. Min Range: -8.4601
Max Act: 8.2726. Min Act: -0.1700
Data Index: 6153417 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4601. Min Range: -8.4601
Max Act: 8.2726. Min Act: -0.1700
Data Index: 8117599 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4601. Min Range: -8.4601
Max Act: 8.2101. Min Act: -0.1700
Data Index: 2986349 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4601. Min Range: -8.4601
Max Act: 8.2101. Min Act: -0.1700
Data Index: 4335409 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4601. Min Range: -8.4601
Max Act: 8.2101. Min Act: -0.1700
Data Index: 4777693 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4601. Min Range: -8.4601
Max Act: 8.1476. Min Act: -0.1700
Data Index: 4697261 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4601. Min Range: -8.4601
Max Act: 8.1476. Min Act: -0.1700
Data Index: 7652705 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4601. Min Range: -8.4601
Max Act: 8.2101. Min Act: -0.1700
Data Index: 2187817 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4601. Min Range: -8.4601
Max Act: 8.1476. Min Act: -0.1700
Data Index: 208099 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4601. Min Range: -8.4601
Max Act: 8.1476. Min Act: -0.1700
Data Index: 4985847 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4601. Min Range: -8.4601
Max Act: 8.1476. Min Act: -0.1700
Data Index: 5249710 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4601. Min Range: -8.4601
Max Act: 8.1476. Min Act: -0.1700
Data Index: 7565821 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4601. Min Range: -8.4601
Max Act: 8.1164. Min Act: -0.1700
Data Index: 803600 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4601. Min Range: -8.4601
Max Act: 8.1476. Min Act: -0.1700
Data Index: 279900 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #19