Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5165 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2526. Min Range: -6.2526
Max Act: 6.2526. Min Act: -0.1700
Data Index: 3951740 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2526. Min Range: -6.2526
Max Act: 6.1901. Min Act: -0.1700
Data Index: 7814724 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2526. Min Range: -6.2526
Max Act: 6.0651. Min Act: -0.1700
Data Index: 1499164 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2526. Min Range: -6.2526
Max Act: 6.0339. Min Act: -0.1700
Data Index: 7593743 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2526. Min Range: -6.2526
Max Act: 6.0026. Min Act: -0.1700
Data Index: 4469752 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2526. Min Range: -6.2526
Max Act: 5.9401. Min Act: -0.1700
Data Index: 6346081 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2526. Min Range: -6.2526
Max Act: 5.8776. Min Act: -0.1700
Data Index: 2530737 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2526. Min Range: -6.2526
Max Act: 5.7839. Min Act: -0.1700
Data Index: 6508674 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2526. Min Range: -6.2526
Max Act: 5.7526. Min Act: -0.1700
Data Index: 8021649 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2526. Min Range: -6.2526
Max Act: 5.7214. Min Act: -0.1700
Data Index: 2907898 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2526. Min Range: -6.2526
Max Act: 5.7214. Min Act: -0.1700
Data Index: 6580570 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2526. Min Range: -6.2526
Max Act: 5.7214. Min Act: -0.1700
Data Index: 7123623 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2526. Min Range: -6.2526
Max Act: 5.7214. Min Act: -0.1700
Data Index: 609800 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2526. Min Range: -6.2526
Max Act: 5.7214. Min Act: -0.1700
Data Index: 6461561 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2526. Min Range: -6.2526
Max Act: 5.6901. Min Act: -0.1700
Data Index: 898493 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2526. Min Range: -6.2526
Max Act: 5.6901. Min Act: -0.1700
Data Index: 7396296 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2526. Min Range: -6.2526
Max Act: 5.7214. Min Act: -0.1700
Data Index: 6961421 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2526. Min Range: -6.2526
Max Act: 5.6589. Min Act: -0.1700
Data Index: 3803851 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2526. Min Range: -6.2526
Max Act: 5.6589. Min Act: -0.1700
Data Index: 817397 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2526. Min Range: -6.2526
Max Act: 5.6589. Min Act: -0.1700
Data Index: 3273691 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #19