Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 2053 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')
Text #0
Max Range: 7.9479. Min Range: -7.9479
Max Act: 7.9479. Min Act: -0.1700
Data Index: 3947903 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9479. Min Range: -7.9479
Max Act: 7.9479. Min Act: -0.1700
Data Index: 3705933 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9479. Min Range: -7.9479
Max Act: 7.9479. Min Act: -0.1700
Data Index: 7892524 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9479. Min Range: -7.9479
Max Act: 7.7917. Min Act: -0.1700
Data Index: 6750420 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9479. Min Range: -7.9479
Max Act: 7.7917. Min Act: -0.1700
Data Index: 7624451 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9479. Min Range: -7.9479
Max Act: 7.8542. Min Act: -0.1700
Data Index: 5741032 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9479. Min Range: -7.9479
Max Act: 7.8229. Min Act: -0.1700
Data Index: 1835444 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9479. Min Range: -7.9479
Max Act: 7.7604. Min Act: -0.1700
Data Index: 4080371 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9479. Min Range: -7.9479
Max Act: 7.7604. Min Act: -0.1700
Data Index: 7442822 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9479. Min Range: -7.9479
Max Act: 7.7604. Min Act: -0.1700
Data Index: 1582569 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9479. Min Range: -7.9479
Max Act: 7.7604. Min Act: -0.1700
Data Index: 2073940 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9479. Min Range: -7.9479
Max Act: 7.7604. Min Act: -0.1700
Data Index: 4652477 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9479. Min Range: -7.9479
Max Act: 7.6979. Min Act: -0.1700
Data Index: 506154 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9479. Min Range: -7.9479
Max Act: 7.6979. Min Act: -0.1700
Data Index: 4318292 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9479. Min Range: -7.9479
Max Act: 7.6979. Min Act: -0.1700
Data Index: 362657 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9479. Min Range: -7.9479
Max Act: 7.6667. Min Act: -0.1700
Data Index: 4291496 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9479. Min Range: -7.9479
Max Act: 7.6667. Min Act: -0.1700
Data Index: 6371875 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9479. Min Range: -7.9479
Max Act: 7.6667. Min Act: -0.1700
Data Index: 4043300 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9479. Min Range: -7.9479
Max Act: 7.6042. Min Act: -0.1700
Data Index: 4983286 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9479. Min Range: -7.9479
Max Act: 7.6667. Min Act: -0.1700
Data Index: 118579 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #19