Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2304 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.6034. Min Range: -8.6034
Max Act: 8.6034. Min Act: -0.1700
Data Index: 1309085 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6034. Min Range: -8.6034
Max Act: 8.2909. Min Act: -0.1700
Data Index: 4338326 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6034. Min Range: -8.6034
Max Act: 8.2909. Min Act: -0.1700
Data Index: 7222984 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6034. Min Range: -8.6034
Max Act: 8.1659. Min Act: -0.1700
Data Index: 323329 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6034. Min Range: -8.6034
Max Act: 8.1034. Min Act: -0.1700
Data Index: 6119065 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6034. Min Range: -8.6034
Max Act: 7.9784. Min Act: -0.1700
Data Index: 5124359 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6034. Min Range: -8.6034
Max Act: 7.9784. Min Act: -0.1700
Data Index: 7482477 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6034. Min Range: -8.6034
Max Act: 7.9159. Min Act: -0.1700
Data Index: 6292441 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6034. Min Range: -8.6034
Max Act: 7.9159. Min Act: -0.1700
Data Index: 1589267 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6034. Min Range: -8.6034
Max Act: 7.9159. Min Act: -0.1700
Data Index: 5722047 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6034. Min Range: -8.6034
Max Act: 7.9159. Min Act: -0.1700
Data Index: 4765180 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6034. Min Range: -8.6034
Max Act: 7.8534. Min Act: -0.1700
Data Index: 7484680 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6034. Min Range: -8.6034
Max Act: 7.8534. Min Act: -0.1700
Data Index: 5863420 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6034. Min Range: -8.6034
Max Act: 7.8534. Min Act: -0.1700
Data Index: 8083586 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6034. Min Range: -8.6034
Max Act: 7.8534. Min Act: -0.1700
Data Index: 5578418 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6034. Min Range: -8.6034
Max Act: 7.8534. Min Act: -0.1700
Data Index: 7222983 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6034. Min Range: -8.6034
Max Act: 7.8534. Min Act: -0.1700
Data Index: 7627824 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6034. Min Range: -8.6034
Max Act: 7.8534. Min Act: -0.1700
Data Index: 2719940 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6034. Min Range: -8.6034
Max Act: 7.7909. Min Act: -0.1700
Data Index: 2146741 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6034. Min Range: -8.6034
Max Act: 7.8534. Min Act: -0.1700
Data Index: 5145023 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #19