Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 81 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.9572. Min Range: -6.9572
Max Act: 6.9572. Min Act: -0.1700
Data Index: 3298511 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9572. Min Range: -6.9572
Max Act: 6.7697. Min Act: -0.1700
Data Index: 3382265 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9572. Min Range: -6.9572
Max Act: 6.7072. Min Act: -0.1700
Data Index: 6203827 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9572. Min Range: -6.9572
Max Act: 6.6447. Min Act: -0.1700
Data Index: 3274656 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9572. Min Range: -6.9572
Max Act: 6.6447. Min Act: -0.1700
Data Index: 1281298 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9572. Min Range: -6.9572
Max Act: 6.5822. Min Act: -0.1700
Data Index: 7843076 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9572. Min Range: -6.9572
Max Act: 6.5509. Min Act: -0.1700
Data Index: 5824726 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9572. Min Range: -6.9572
Max Act: 6.5509. Min Act: -0.1700
Data Index: 6816910 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9572. Min Range: -6.9572
Max Act: 6.5509. Min Act: -0.1700
Data Index: 2746083 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9572. Min Range: -6.9572
Max Act: 6.5509. Min Act: -0.1700
Data Index: 4677403 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9572. Min Range: -6.9572
Max Act: 6.5509. Min Act: -0.1700
Data Index: 7598348 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9572. Min Range: -6.9572
Max Act: 6.5197. Min Act: -0.1700
Data Index: 78719 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9572. Min Range: -6.9572
Max Act: 6.5509. Min Act: -0.1700
Data Index: 5070080 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9572. Min Range: -6.9572
Max Act: 6.5197. Min Act: -0.1700
Data Index: 8222303 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9572. Min Range: -6.9572
Max Act: 6.5197. Min Act: -0.1700
Data Index: 7363007 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9572. Min Range: -6.9572
Max Act: 6.4572. Min Act: -0.1700
Data Index: 4650021 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9572. Min Range: -6.9572
Max Act: 6.4884. Min Act: -0.1700
Data Index: 3624547 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9572. Min Range: -6.9572
Max Act: 6.5197. Min Act: -0.1700
Data Index: 837826 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9572. Min Range: -6.9572
Max Act: 6.4572. Min Act: -0.1700
Data Index: 5551366 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9572. Min Range: -6.9572
Max Act: 6.4572. Min Act: -0.1700
Data Index: 1052567 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #19