Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4373 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.8683. Min Range: -9.8683
Max Act: 9.8683. Min Act: -0.1700
Data Index: 4372167 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.8683. Min Range: -9.8683
Max Act: 9.3683. Min Act: -0.1700
Data Index: 2308181 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.8683. Min Range: -9.8683
Max Act: 9.2433. Min Act: -0.1700
Data Index: 98548 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.8683. Min Range: -9.8683
Max Act: 9.1183. Min Act: -0.1700
Data Index: 4161542 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.8683. Min Range: -9.8683
Max Act: 9.0558. Min Act: -0.1700
Data Index: 2105259 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.8683. Min Range: -9.8683
Max Act: 8.9933. Min Act: -0.1700
Data Index: 7674252 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.8683. Min Range: -9.8683
Max Act: 8.9933. Min Act: -0.1700
Data Index: 972192 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.8683. Min Range: -9.8683
Max Act: 8.9308. Min Act: -0.1700
Data Index: 6928756 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.8683. Min Range: -9.8683
Max Act: 8.9308. Min Act: -0.1700
Data Index: 1057087 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.8683. Min Range: -9.8683
Max Act: 8.9308. Min Act: -0.1700
Data Index: 5754076 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.8683. Min Range: -9.8683
Max Act: 8.9308. Min Act: -0.1700
Data Index: 7697651 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.8683. Min Range: -9.8683
Max Act: 8.8683. Min Act: -0.1700
Data Index: 3545733 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.8683. Min Range: -9.8683
Max Act: 8.8683. Min Act: -0.1700
Data Index: 6840330 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.8683. Min Range: -9.8683
Max Act: 8.8683. Min Act: -0.1700
Data Index: 2160631 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.8683. Min Range: -9.8683
Max Act: 8.8683. Min Act: -0.1700
Data Index: 906586 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.8683. Min Range: -9.8683
Max Act: 8.8058. Min Act: -0.1700
Data Index: 3051289 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.8683. Min Range: -9.8683
Max Act: 8.8058. Min Act: -0.1700
Data Index: 3814939 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.8683. Min Range: -9.8683
Max Act: 8.7433. Min Act: -0.1699
Data Index: 3667501 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.8683. Min Range: -9.8683
Max Act: 8.7433. Min Act: -0.1700
Data Index: 8351818 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.8683. Min Range: -9.8683
Max Act: 8.6183. Min Act: -0.1700
Data Index: 2456372 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #19