Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2957 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5284. Min Range: -6.5284
Max Act: 6.5284. Min Act: -0.1700
Data Index: 7238329 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5284. Min Range: -6.5284
Max Act: 6.4972. Min Act: -0.1700
Data Index: 56042 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5284. Min Range: -6.5284
Max Act: 6.4034. Min Act: -0.1700
Data Index: 8336169 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5284. Min Range: -6.5284
Max Act: 6.3409. Min Act: -0.1700
Data Index: 1028498 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5284. Min Range: -6.5284
Max Act: 6.2784. Min Act: -0.1700
Data Index: 6422064 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5284. Min Range: -6.5284
Max Act: 6.2784. Min Act: -0.1700
Data Index: 2089333 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5284. Min Range: -6.5284
Max Act: 6.2159. Min Act: -0.1700
Data Index: 3243099 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5284. Min Range: -6.5284
Max Act: 6.1847. Min Act: -0.1700
Data Index: 2607892 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5284. Min Range: -6.5284
Max Act: 6.1847. Min Act: -0.1698
Data Index: 3834900 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5284. Min Range: -6.5284
Max Act: 6.1847. Min Act: -0.1700
Data Index: 7457364 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5284. Min Range: -6.5284
Max Act: 6.1847. Min Act: -0.1700
Data Index: 1503242 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5284. Min Range: -6.5284
Max Act: 6.1534. Min Act: -0.1700
Data Index: 2201394 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5284. Min Range: -6.5284
Max Act: 6.1534. Min Act: -0.1700
Data Index: 6621844 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5284. Min Range: -6.5284
Max Act: 6.1222. Min Act: -0.1700
Data Index: 2584672 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5284. Min Range: -6.5284
Max Act: 6.1534. Min Act: -0.1700
Data Index: 6511359 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5284. Min Range: -6.5284
Max Act: 6.1534. Min Act: -0.1700
Data Index: 5659936 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5284. Min Range: -6.5284
Max Act: 6.1222. Min Act: -0.1700
Data Index: 2653449 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5284. Min Range: -6.5284
Max Act: 6.1222. Min Act: -0.1700
Data Index: 2089322 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5284. Min Range: -6.5284
Max Act: 6.1222. Min Act: -0.1700
Data Index: 8219974 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5284. Min Range: -6.5284
Max Act: 6.0909. Min Act: -0.1700
Data Index: 6304817 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #19