Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 433 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1762. Min Range: -5.1762
Max Act: 5.1762. Min Act: -0.1700
Data Index: 39615 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1762. Min Range: -5.1762
Max Act: 4.9887. Min Act: -0.1700
Data Index: 984486 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1762. Min Range: -5.1762
Max Act: 4.9887. Min Act: -0.1700
Data Index: 6431398 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1762. Min Range: -5.1762
Max Act: 4.9887. Min Act: -0.1700
Data Index: 688030 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1762. Min Range: -5.1762
Max Act: 4.9262. Min Act: -0.1700
Data Index: 6490034 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1762. Min Range: -5.1762
Max Act: 4.8949. Min Act: -0.1700
Data Index: 5623458 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1762. Min Range: -5.1762
Max Act: 4.8949. Min Act: -0.1700
Data Index: 8495472 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1762. Min Range: -5.1762
Max Act: 4.8637. Min Act: -0.1700
Data Index: 3889279 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1762. Min Range: -5.1762
Max Act: 4.8637. Min Act: -0.1700
Data Index: 4637484 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1762. Min Range: -5.1762
Max Act: 4.8637. Min Act: -0.1700
Data Index: 7011770 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1762. Min Range: -5.1762
Max Act: 4.8637. Min Act: -0.1700
Data Index: 8556987 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1762. Min Range: -5.1762
Max Act: 4.8324. Min Act: -0.1700
Data Index: 3049987 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1762. Min Range: -5.1762
Max Act: 4.8324. Min Act: -0.1700
Data Index: 1412867 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1762. Min Range: -5.1762
Max Act: 4.8324. Min Act: -0.1700
Data Index: 6716534 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1762. Min Range: -5.1762
Max Act: 4.8324. Min Act: -0.1700
Data Index: 5219992 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1762. Min Range: -5.1762
Max Act: 4.8324. Min Act: -0.1700
Data Index: 8421858 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1762. Min Range: -5.1762
Max Act: 4.8324. Min Act: -0.1700
Data Index: 5154342 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1762. Min Range: -5.1762
Max Act: 4.8324. Min Act: -0.1700
Data Index: 1691069 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1762. Min Range: -5.1762
Max Act: 4.8012. Min Act: -0.1700
Data Index: 7206694 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1762. Min Range: -5.1762
Max Act: 4.8012. Min Act: -0.1700
Data Index: 8352756 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #19