Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1568 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.3340. Min Range: -4.3340
Max Act: 4.3340. Min Act: -0.1700
Data Index: 3759525 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3340. Min Range: -4.3340
Max Act: 4.1778. Min Act: -0.1700
Data Index: 5022928 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3340. Min Range: -4.3340
Max Act: 4.1465. Min Act: -0.1700
Data Index: 3670201 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3340. Min Range: -4.3340
Max Act: 4.1465. Min Act: -0.1700
Data Index: 4586373 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3340. Min Range: -4.3340
Max Act: 4.1465. Min Act: -0.1700
Data Index: 3470653 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3340. Min Range: -4.3340
Max Act: 4.1465. Min Act: -0.1700
Data Index: 3893504 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3340. Min Range: -4.3340
Max Act: 4.0840. Min Act: -0.1700
Data Index: 2101874 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3340. Min Range: -4.3340
Max Act: 4.1153. Min Act: -0.1700
Data Index: 7253405 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3340. Min Range: -4.3340
Max Act: 4.0527. Min Act: -0.1700
Data Index: 3434628 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3340. Min Range: -4.3340
Max Act: 4.0840. Min Act: -0.1700
Data Index: 3466515 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3340. Min Range: -4.3340
Max Act: 4.0840. Min Act: -0.1700
Data Index: 1729746 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3340. Min Range: -4.3340
Max Act: 4.0840. Min Act: -0.1700
Data Index: 4987270 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3340. Min Range: -4.3340
Max Act: 4.0840. Min Act: -0.1700
Data Index: 1484573 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3340. Min Range: -4.3340
Max Act: 4.0840. Min Act: -0.1700
Data Index: 4286495 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3340. Min Range: -4.3340
Max Act: 4.0215. Min Act: -0.1700
Data Index: 5428527 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3340. Min Range: -4.3340
Max Act: 4.0527. Min Act: -0.1700
Data Index: 4143583 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3340. Min Range: -4.3340
Max Act: 4.0527. Min Act: -0.1700
Data Index: 3253455 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3340. Min Range: -4.3340
Max Act: 4.0215. Min Act: -0.1700
Data Index: 494966 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3340. Min Range: -4.3340
Max Act: 4.0840. Min Act: -0.1700
Data Index: 5746349 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3340. Min Range: -4.3340
Max Act: 4.0527. Min Act: -0.1700
Data Index: 1529818 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #19