Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4384 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2465. Min Range: -6.2465
Max Act: 6.2465. Min Act: -0.1700
Data Index: 2935090 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2465. Min Range: -6.2465
Max Act: 6.1527. Min Act: -0.1700
Data Index: 2130333 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2465. Min Range: -6.2465
Max Act: 5.9965. Min Act: -0.1700
Data Index: 5555245 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2465. Min Range: -6.2465
Max Act: 5.9965. Min Act: -0.1700
Data Index: 3898191 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2465. Min Range: -6.2465
Max Act: 5.9652. Min Act: -0.1700
Data Index: 1979108 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2465. Min Range: -6.2465
Max Act: 5.9652. Min Act: -0.1700
Data Index: 4974222 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2465. Min Range: -6.2465
Max Act: 5.9027. Min Act: -0.1700
Data Index: 4918165 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2465. Min Range: -6.2465
Max Act: 5.9027. Min Act: -0.1700
Data Index: 1521007 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2465. Min Range: -6.2465
Max Act: 5.9027. Min Act: -0.1700
Data Index: 2050835 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2465. Min Range: -6.2465
Max Act: 5.8715. Min Act: -0.1700
Data Index: 5714448 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2465. Min Range: -6.2465
Max Act: 5.8715. Min Act: -0.1700
Data Index: 6170269 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2465. Min Range: -6.2465
Max Act: 5.8402. Min Act: -0.1700
Data Index: 8029667 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2465. Min Range: -6.2465
Max Act: 5.8402. Min Act: -0.1700
Data Index: 4942174 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2465. Min Range: -6.2465
Max Act: 5.8402. Min Act: -0.1700
Data Index: 2998732 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2465. Min Range: -6.2465
Max Act: 5.8090. Min Act: -0.1700
Data Index: 4693724 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2465. Min Range: -6.2465
Max Act: 5.8090. Min Act: -0.1700
Data Index: 7032793 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2465. Min Range: -6.2465
Max Act: 5.8090. Min Act: -0.1700
Data Index: 2486698 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2465. Min Range: -6.2465
Max Act: 5.8402. Min Act: -0.1700
Data Index: 7774252 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2465. Min Range: -6.2465
Max Act: 5.8090. Min Act: -0.1700
Data Index: 4364343 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2465. Min Range: -6.2465
Max Act: 5.7777. Min Act: -0.1700
Data Index: 1633771 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #19