Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3212 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5803. Min Range: -5.5803
Max Act: 5.5803. Min Act: -0.1700
Data Index: 1998885 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5803. Min Range: -5.5803
Max Act: 5.4866. Min Act: -0.1700
Data Index: 3386904 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5803. Min Range: -5.5803
Max Act: 5.2991. Min Act: -0.1700
Data Index: 5645756 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5803. Min Range: -5.5803
Max Act: 5.2678. Min Act: -0.1700
Data Index: 6842143 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5803. Min Range: -5.5803
Max Act: 5.2678. Min Act: -0.1700
Data Index: 4403617 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5803. Min Range: -5.5803
Max Act: 5.2366. Min Act: -0.1700
Data Index: 14850 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5803. Min Range: -5.5803
Max Act: 5.1741. Min Act: -0.1700
Data Index: 5217790 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5803. Min Range: -5.5803
Max Act: 5.2053. Min Act: -0.1700
Data Index: 6528429 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5803. Min Range: -5.5803
Max Act: 5.1428. Min Act: -0.1700
Data Index: 2282694 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5803. Min Range: -5.5803
Max Act: 5.1116. Min Act: -0.1700
Data Index: 4204720 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5803. Min Range: -5.5803
Max Act: 5.0803. Min Act: -0.1700
Data Index: 6915953 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5803. Min Range: -5.5803
Max Act: 5.0803. Min Act: -0.1700
Data Index: 5318574 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5803. Min Range: -5.5803
Max Act: 5.0803. Min Act: -0.1700
Data Index: 1839576 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5803. Min Range: -5.5803
Max Act: 5.0491. Min Act: -0.1700
Data Index: 1253306 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5803. Min Range: -5.5803
Max Act: 5.0491. Min Act: -0.1700
Data Index: 3691291 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5803. Min Range: -5.5803
Max Act: 5.0178. Min Act: -0.1700
Data Index: 2578377 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5803. Min Range: -5.5803
Max Act: 5.0178. Min Act: -0.1700
Data Index: 5465043 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5803. Min Range: -5.5803
Max Act: 5.0178. Min Act: -0.1700
Data Index: 2190907 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5803. Min Range: -5.5803
Max Act: 4.9866. Min Act: -0.1700
Data Index: 2838633 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5803. Min Range: -5.5803
Max Act: 5.0178. Min Act: -0.1700
Data Index: 125293 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #19