Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2417 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.3256. Min Range: -6.3256
Max Act: 6.3256. Min Act: -0.1700
Data Index: 473109 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3256. Min Range: -6.3256
Max Act: 6.0756. Min Act: -0.1700
Data Index: 5742873 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3256. Min Range: -6.3256
Max Act: 6.0131. Min Act: -0.1700
Data Index: 1176370 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3256. Min Range: -6.3256
Max Act: 5.9506. Min Act: -0.1700
Data Index: 8481061 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3256. Min Range: -6.3256
Max Act: 5.9818. Min Act: -0.1700
Data Index: 3275968 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3256. Min Range: -6.3256
Max Act: 5.9506. Min Act: -0.1700
Data Index: 4965573 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3256. Min Range: -6.3256
Max Act: 5.9506. Min Act: -0.1700
Data Index: 1781756 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3256. Min Range: -6.3256
Max Act: 5.9506. Min Act: -0.1700
Data Index: 6917292 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3256. Min Range: -6.3256
Max Act: 5.9193. Min Act: -0.1700
Data Index: 6942690 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3256. Min Range: -6.3256
Max Act: 5.9193. Min Act: -0.1700
Data Index: 2127477 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3256. Min Range: -6.3256
Max Act: 5.9506. Min Act: -0.1700
Data Index: 3782239 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3256. Min Range: -6.3256
Max Act: 5.9506. Min Act: -0.1700
Data Index: 8135792 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3256. Min Range: -6.3256
Max Act: 5.9193. Min Act: -0.1700
Data Index: 5156551 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3256. Min Range: -6.3256
Max Act: 5.9193. Min Act: -0.1700
Data Index: 8228616 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3256. Min Range: -6.3256
Max Act: 5.9193. Min Act: -0.1700
Data Index: 5052087 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3256. Min Range: -6.3256
Max Act: 5.8881. Min Act: -0.1700
Data Index: 3203009 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3256. Min Range: -6.3256
Max Act: 5.8881. Min Act: -0.1700
Data Index: 5303299 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3256. Min Range: -6.3256
Max Act: 5.8881. Min Act: -0.1700
Data Index: 7299808 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3256. Min Range: -6.3256
Max Act: 5.8881. Min Act: -0.1700
Data Index: 6764660 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3256. Min Range: -6.3256
Max Act: 5.8568. Min Act: -0.1700
Data Index: 7911821 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #19