Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1373 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 9.0326. Min Range: -9.0326
Max Act: 9.0326. Min Act: -0.1700
Data Index: 4966958 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0326. Min Range: -9.0326
Max Act: 8.9701. Min Act: -0.1700
Data Index: 168417 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0326. Min Range: -9.0326
Max Act: 8.8451. Min Act: -0.1700
Data Index: 4768449 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0326. Min Range: -9.0326
Max Act: 8.8451. Min Act: -0.1700
Data Index: 6306005 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0326. Min Range: -9.0326
Max Act: 8.7826. Min Act: -0.1700
Data Index: 488693 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0326. Min Range: -9.0326
Max Act: 8.7826. Min Act: -0.1700
Data Index: 7280890 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0326. Min Range: -9.0326
Max Act: 8.7201. Min Act: -0.1700
Data Index: 467566 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0326. Min Range: -9.0326
Max Act: 8.6576. Min Act: -0.1700
Data Index: 934240 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0326. Min Range: -9.0326
Max Act: 8.6576. Min Act: -0.1700
Data Index: 3396833 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0326. Min Range: -9.0326
Max Act: 8.6576. Min Act: -0.1700
Data Index: 3188826 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0326. Min Range: -9.0326
Max Act: 8.6576. Min Act: -0.1700
Data Index: 3923676 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0326. Min Range: -9.0326
Max Act: 8.6576. Min Act: -0.1700
Data Index: 8317357 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0326. Min Range: -9.0326
Max Act: 8.6576. Min Act: -0.1700
Data Index: 2942094 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0326. Min Range: -9.0326
Max Act: 8.6576. Min Act: -0.1700
Data Index: 5606090 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0326. Min Range: -9.0326
Max Act: 8.5951. Min Act: -0.1700
Data Index: 2989988 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0326. Min Range: -9.0326
Max Act: 8.5326. Min Act: -0.1700
Data Index: 1290476 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0326. Min Range: -9.0326
Max Act: 8.5951. Min Act: -0.1700
Data Index: 5070110 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0326. Min Range: -9.0326
Max Act: 8.5951. Min Act: -0.1700
Data Index: 5195025 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0326. Min Range: -9.0326
Max Act: 8.5326. Min Act: -0.1700
Data Index: 5385184 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0326. Min Range: -9.0326
Max Act: 8.5951. Min Act: -0.1700
Data Index: 4746991 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #19