Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2889 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0164. Min Range: -7.0164
Max Act: 7.0164. Min Act: -0.1700
Data Index: 3529113 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0164. Min Range: -7.0164
Max Act: 6.7351. Min Act: -0.1700
Data Index: 752526 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0164. Min Range: -7.0164
Max Act: 6.2976. Min Act: -0.1700
Data Index: 970657 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0164. Min Range: -7.0164
Max Act: 6.2976. Min Act: -0.1700
Data Index: 5193316 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0164. Min Range: -7.0164
Max Act: 6.2976. Min Act: -0.1700
Data Index: 361946 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0164. Min Range: -7.0164
Max Act: 6.2664. Min Act: -0.1700
Data Index: 3587437 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0164. Min Range: -7.0164
Max Act: 6.2664. Min Act: -0.1700
Data Index: 2597776 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0164. Min Range: -7.0164
Max Act: 6.2664. Min Act: -0.1700
Data Index: 3595648 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0164. Min Range: -7.0164
Max Act: 6.2351. Min Act: -0.1700
Data Index: 6769932 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0164. Min Range: -7.0164
Max Act: 6.2351. Min Act: -0.1700
Data Index: 1930107 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0164. Min Range: -7.0164
Max Act: 6.2039. Min Act: -0.1700
Data Index: 3143875 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0164. Min Range: -7.0164
Max Act: 6.2039. Min Act: -0.1700
Data Index: 531491 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0164. Min Range: -7.0164
Max Act: 6.1414. Min Act: -0.1700
Data Index: 6212608 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0164. Min Range: -7.0164
Max Act: 6.1414. Min Act: -0.1700
Data Index: 1227609 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0164. Min Range: -7.0164
Max Act: 6.1414. Min Act: -0.1700
Data Index: 760288 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0164. Min Range: -7.0164
Max Act: 6.1726. Min Act: -0.1700
Data Index: 3393011 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0164. Min Range: -7.0164
Max Act: 6.1101. Min Act: -0.1700
Data Index: 2290263 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0164. Min Range: -7.0164
Max Act: 6.1101. Min Act: -0.1700
Data Index: 3623885 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0164. Min Range: -7.0164
Max Act: 6.0789. Min Act: -0.1700
Data Index: 462287 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0164. Min Range: -7.0164
Max Act: 6.0789. Min Act: -0.1700
Data Index: 412784 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #19