Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3576 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.4891. Min Range: -1.4891
Max Act: 1.4891. Min Act: -0.1700
Data Index: 4906280 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.4891. Min Range: -1.4891
Max Act: 1.4452. Min Act: -0.1700
Data Index: 1727722 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.4891. Min Range: -1.4891
Max Act: 1.4364. Min Act: -0.1700
Data Index: 1496330 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.4891. Min Range: -1.4891
Max Act: 1.4452. Min Act: -0.1700
Data Index: 5943977 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.4891. Min Range: -1.4891
Max Act: 1.4452. Min Act: -0.1700
Data Index: 802392 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.4891. Min Range: -1.4891
Max Act: 1.4188. Min Act: -0.1700
Data Index: 8533956 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.4891. Min Range: -1.4891
Max Act: 1.4276. Min Act: -0.1700
Data Index: 6072384 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.4891. Min Range: -1.4891
Max Act: 1.4276. Min Act: -0.1700
Data Index: 8516303 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.4891. Min Range: -1.4891
Max Act: 1.4276. Min Act: -0.1700
Data Index: 7601776 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.4891. Min Range: -1.4891
Max Act: 1.4188. Min Act: -0.1700
Data Index: 272884 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.4891. Min Range: -1.4891
Max Act: 1.4188. Min Act: -0.1700
Data Index: 4215558 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.4891. Min Range: -1.4891
Max Act: 1.4276. Min Act: -0.1700
Data Index: 3659888 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.4891. Min Range: -1.4891
Max Act: 1.4099. Min Act: -0.1700
Data Index: 3117408 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.4891. Min Range: -1.4891
Max Act: 1.4099. Min Act: -0.1700
Data Index: 7839201 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.4891. Min Range: -1.4891
Max Act: 1.4099. Min Act: -0.1700
Data Index: 8590838 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.4891. Min Range: -1.4891
Max Act: 1.4099. Min Act: -0.1700
Data Index: 3220115 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.4891. Min Range: -1.4891
Max Act: 1.3923. Min Act: -0.1700
Data Index: 5407521 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.4891. Min Range: -1.4891
Max Act: 1.3923. Min Act: -0.1700
Data Index: 4699791 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.4891. Min Range: -1.4891
Max Act: 1.4011. Min Act: -0.1700
Data Index: 7625804 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.4891. Min Range: -1.4891
Max Act: 1.3923. Min Act: -0.1700
Data Index: 223612 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #19