Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3550 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.0108. Min Range: -2.0108
Max Act: 2.0108. Min Act: -0.1687
Data Index: 1970604 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0108. Min Range: -2.0108
Max Act: 2.0024. Min Act: -0.1700
Data Index: 6900108 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0108. Min Range: -2.0108
Max Act: 1.9855. Min Act: -0.1700
Data Index: 5042726 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0108. Min Range: -2.0108
Max Act: 1.9855. Min Act: -0.1700
Data Index: 1627278 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0108. Min Range: -2.0108
Max Act: 1.9685. Min Act: -0.1700
Data Index: 3228112 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0108. Min Range: -2.0108
Max Act: 1.9685. Min Act: -0.1700
Data Index: 2215094 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0108. Min Range: -2.0108
Max Act: 1.9685. Min Act: -0.1700
Data Index: 899018 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0108. Min Range: -2.0108
Max Act: 1.9685. Min Act: -0.1700
Data Index: 1538930 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0108. Min Range: -2.0108
Max Act: 1.9600. Min Act: -0.1700
Data Index: 5380913 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0108. Min Range: -2.0108
Max Act: 1.9346. Min Act: -0.1699
Data Index: 2093196 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0108. Min Range: -2.0108
Max Act: 1.9346. Min Act: -0.1700
Data Index: 5077635 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0108. Min Range: -2.0108
Max Act: 1.9431. Min Act: -0.1700
Data Index: 6109139 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0108. Min Range: -2.0108
Max Act: 1.9431. Min Act: -0.1700
Data Index: 1006205 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0108. Min Range: -2.0108
Max Act: 1.9431. Min Act: -0.1700
Data Index: 4054564 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0108. Min Range: -2.0108
Max Act: 1.9346. Min Act: -0.1700
Data Index: 3768870 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0108. Min Range: -2.0108
Max Act: 1.9346. Min Act: -0.1699
Data Index: 6025914 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0108. Min Range: -2.0108
Max Act: 1.9346. Min Act: -0.1698
Data Index: 6108457 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0108. Min Range: -2.0108
Max Act: 1.9346. Min Act: -0.1700
Data Index: 3186224 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0108. Min Range: -2.0108
Max Act: 1.9261. Min Act: -0.1700
Data Index: 6299125 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0108. Min Range: -2.0108
Max Act: 1.9176. Min Act: -0.1700
Data Index: 703782 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #19