Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 984 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.1042. Min Range: -5.1042
Max Act: 5.1042. Min Act: -0.1700
Data Index: 1318785 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1042. Min Range: -5.1042
Max Act: 5.0104. Min Act: -0.1700
Data Index: 5410535 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1042. Min Range: -5.1042
Max Act: 4.8854. Min Act: -0.1700
Data Index: 194497 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1042. Min Range: -5.1042
Max Act: 4.8854. Min Act: -0.1700
Data Index: 5141302 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1042. Min Range: -5.1042
Max Act: 4.8854. Min Act: -0.1700
Data Index: 2737045 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1042. Min Range: -5.1042
Max Act: 4.8854. Min Act: -0.1700
Data Index: 5661358 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1042. Min Range: -5.1042
Max Act: 4.8854. Min Act: -0.1700
Data Index: 7082737 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1042. Min Range: -5.1042
Max Act: 4.8854. Min Act: -0.1700
Data Index: 730799 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1042. Min Range: -5.1042
Max Act: 4.8542. Min Act: -0.1700
Data Index: 642744 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1042. Min Range: -5.1042
Max Act: 4.8854. Min Act: -0.1700
Data Index: 979873 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1042. Min Range: -5.1042
Max Act: 4.7917. Min Act: -0.1700
Data Index: 2306576 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1042. Min Range: -5.1042
Max Act: 4.7917. Min Act: -0.1700
Data Index: 3420103 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1042. Min Range: -5.1042
Max Act: 4.8229. Min Act: -0.1700
Data Index: 5973605 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1042. Min Range: -5.1042
Max Act: 4.7604. Min Act: -0.1700
Data Index: 7088160 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1042. Min Range: -5.1042
Max Act: 4.7604. Min Act: -0.1700
Data Index: 7241264 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1042. Min Range: -5.1042
Max Act: 4.7604. Min Act: -0.1700
Data Index: 8352389 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1042. Min Range: -5.1042
Max Act: 4.7604. Min Act: -0.1700
Data Index: 132412 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1042. Min Range: -5.1042
Max Act: 4.7604. Min Act: -0.1700
Data Index: 3822586 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1042. Min Range: -5.1042
Max Act: 4.7604. Min Act: -0.1700
Data Index: 2057750 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1042. Min Range: -5.1042
Max Act: 4.7292. Min Act: -0.1700
Data Index: 3001609 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #19