Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 804 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4121. Min Range: -7.4121
Max Act: 7.4121. Min Act: -0.1700
Data Index: 8738953 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4121. Min Range: -7.4121
Max Act: 7.3496. Min Act: -0.1700
Data Index: 1400414 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4121. Min Range: -7.4121
Max Act: 7.3496. Min Act: -0.1700
Data Index: 4865512 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4121. Min Range: -7.4121
Max Act: 7.3496. Min Act: -0.1700
Data Index: 6458060 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4121. Min Range: -7.4121
Max Act: 7.2871. Min Act: -0.1700
Data Index: 1626410 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4121. Min Range: -7.4121
Max Act: 7.2558. Min Act: -0.1700
Data Index: 2276654 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4121. Min Range: -7.4121
Max Act: 7.1933. Min Act: -0.1700
Data Index: 5479222 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4121. Min Range: -7.4121
Max Act: 7.1933. Min Act: -0.1700
Data Index: 2973086 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4121. Min Range: -7.4121
Max Act: 7.0996. Min Act: -0.1700
Data Index: 8647430 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4121. Min Range: -7.4121
Max Act: 7.0996. Min Act: -0.1700
Data Index: 4212997 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4121. Min Range: -7.4121
Max Act: 7.0996. Min Act: -0.1700
Data Index: 2801385 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4121. Min Range: -7.4121
Max Act: 7.0996. Min Act: -0.1700
Data Index: 3529549 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4121. Min Range: -7.4121
Max Act: 7.0371. Min Act: -0.1700
Data Index: 3968754 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4121. Min Range: -7.4121
Max Act: 7.0058. Min Act: -0.1700
Data Index: 6291272 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4121. Min Range: -7.4121
Max Act: 7.0058. Min Act: -0.1700
Data Index: 8424394 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4121. Min Range: -7.4121
Max Act: 7.0058. Min Act: -0.1700
Data Index: 1610061 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4121. Min Range: -7.4121
Max Act: 6.9746. Min Act: -0.1700
Data Index: 8737995 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4121. Min Range: -7.4121
Max Act: 6.9746. Min Act: -0.1700
Data Index: 7751587 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4121. Min Range: -7.4121
Max Act: 6.9433. Min Act: -0.1700
Data Index: 6302186 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4121. Min Range: -7.4121
Max Act: 6.9433. Min Act: -0.1700
Data Index: 2107344 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #19