Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1974 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.0534. Min Range: -4.0534
Max Act: 4.0534. Min Act: -0.1700
Data Index: 7428400 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0534. Min Range: -4.0534
Max Act: 3.9597. Min Act: -0.1700
Data Index: 4434144 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0534. Min Range: -4.0534
Max Act: 3.8346. Min Act: -0.1700
Data Index: 8205682 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0534. Min Range: -4.0534
Max Act: 3.8346. Min Act: -0.1700
Data Index: 4647282 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0534. Min Range: -4.0534
Max Act: 3.8346. Min Act: -0.1700
Data Index: 2150380 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0534. Min Range: -4.0534
Max Act: 3.8190. Min Act: -0.1700
Data Index: 8644465 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0534. Min Range: -4.0534
Max Act: 3.7877. Min Act: -0.1700
Data Index: 7302812 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0534. Min Range: -4.0534
Max Act: 3.7251. Min Act: -0.1700
Data Index: 8764320 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0534. Min Range: -4.0534
Max Act: 3.7564. Min Act: -0.1700
Data Index: 2177592 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0534. Min Range: -4.0534
Max Act: 3.7251. Min Act: -0.1700
Data Index: 6472659 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0534. Min Range: -4.0534
Max Act: 3.7877. Min Act: -0.1700
Data Index: 4661903 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0534. Min Range: -4.0534
Max Act: 3.7251. Min Act: -0.1700
Data Index: 2240862 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0534. Min Range: -4.0534
Max Act: 3.7564. Min Act: -0.1700
Data Index: 6845197 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0534. Min Range: -4.0534
Max Act: 3.6782. Min Act: -0.1700
Data Index: 7525726 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0534. Min Range: -4.0534
Max Act: 3.6782. Min Act: -0.1700
Data Index: 4744426 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0534. Min Range: -4.0534
Max Act: 3.6938. Min Act: -0.1700
Data Index: 1628572 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0534. Min Range: -4.0534
Max Act: 3.6782. Min Act: -0.1700
Data Index: 7794294 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0534. Min Range: -4.0534
Max Act: 3.7251. Min Act: -0.1700
Data Index: 758403 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0534. Min Range: -4.0534
Max Act: 3.6938. Min Act: -0.1700
Data Index: 7711284 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0534. Min Range: -4.0534
Max Act: 3.6626. Min Act: -0.1700
Data Index: 4778269 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #19