Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1945 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.5496. Min Range: -5.5496
Max Act: 5.5496. Min Act: -0.1700
Data Index: 8487401 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5496. Min Range: -5.5496
Max Act: 5.3933. Min Act: -0.1700
Data Index: 418542 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5496. Min Range: -5.5496
Max Act: 5.4558. Min Act: -0.1699
Data Index: 6184908 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5496. Min Range: -5.5496
Max Act: 5.4246. Min Act: -0.1700
Data Index: 6094824 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5496. Min Range: -5.5496
Max Act: 5.3933. Min Act: -0.1700
Data Index: 7046684 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5496. Min Range: -5.5496
Max Act: 5.4246. Min Act: -0.1700
Data Index: 1984194 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5496. Min Range: -5.5496
Max Act: 5.3621. Min Act: -0.1700
Data Index: 821717 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5496. Min Range: -5.5496
Max Act: 5.3933. Min Act: -0.1700
Data Index: 8622558 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5496. Min Range: -5.5496
Max Act: 5.3933. Min Act: -0.1700
Data Index: 7016453 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5496. Min Range: -5.5496
Max Act: 5.3621. Min Act: -0.1700
Data Index: 1984191 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5496. Min Range: -5.5496
Max Act: 5.3621. Min Act: -0.1700
Data Index: 3622676 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5496. Min Range: -5.5496
Max Act: 5.3308. Min Act: -0.1700
Data Index: 2961105 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5496. Min Range: -5.5496
Max Act: 5.3621. Min Act: -0.1700
Data Index: 2094448 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5496. Min Range: -5.5496
Max Act: 5.2996. Min Act: -0.1700
Data Index: 5474715 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5496. Min Range: -5.5496
Max Act: 5.2996. Min Act: -0.1700
Data Index: 2427957 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5496. Min Range: -5.5496
Max Act: 5.3308. Min Act: -0.1700
Data Index: 4498455 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5496. Min Range: -5.5496
Max Act: 5.2996. Min Act: -0.1700
Data Index: 3133054 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5496. Min Range: -5.5496
Max Act: 5.2683. Min Act: -0.1700
Data Index: 3573912 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5496. Min Range: -5.5496
Max Act: 5.2996. Min Act: -0.1699
Data Index: 1174511 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5496. Min Range: -5.5496
Max Act: 5.2683. Min Act: -0.1694
Data Index: 6548980 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #19