Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2581 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.1793. Min Range: -6.1793
Max Act: 6.1793. Min Act: -0.1700
Data Index: 6770217 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1793. Min Range: -6.1793
Max Act: 6.0856. Min Act: -0.1700
Data Index: 4790111 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1793. Min Range: -6.1793
Max Act: 6.0543. Min Act: -0.1700
Data Index: 8232364 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1793. Min Range: -6.1793
Max Act: 6.0543. Min Act: -0.1700
Data Index: 3950160 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1793. Min Range: -6.1793
Max Act: 5.8981. Min Act: -0.1700
Data Index: 2838023 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1793. Min Range: -6.1793
Max Act: 5.8981. Min Act: -0.1700
Data Index: 4758455 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1793. Min Range: -6.1793
Max Act: 5.8668. Min Act: -0.1700
Data Index: 4241458 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1793. Min Range: -6.1793
Max Act: 5.8356. Min Act: -0.1700
Data Index: 2778731 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1793. Min Range: -6.1793
Max Act: 5.7106. Min Act: -0.1700
Data Index: 3233445 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1793. Min Range: -6.1793
Max Act: 5.7106. Min Act: -0.1700
Data Index: 6900604 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1793. Min Range: -6.1793
Max Act: 5.7106. Min Act: -0.1700
Data Index: 285692 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1793. Min Range: -6.1793
Max Act: 5.7106. Min Act: -0.1700
Data Index: 7806432 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1793. Min Range: -6.1793
Max Act: 5.7106. Min Act: -0.1700
Data Index: 1866357 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1793. Min Range: -6.1793
Max Act: 5.6793. Min Act: -0.1700
Data Index: 1504381 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1793. Min Range: -6.1793
Max Act: 5.6793. Min Act: -0.1700
Data Index: 7788431 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1793. Min Range: -6.1793
Max Act: 5.6481. Min Act: -0.1700
Data Index: 8678143 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1793. Min Range: -6.1793
Max Act: 5.6168. Min Act: -0.1700
Data Index: 101908 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1793. Min Range: -6.1793
Max Act: 5.6168. Min Act: -0.1700
Data Index: 4557512 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1793. Min Range: -6.1793
Max Act: 5.6168. Min Act: -0.1700
Data Index: 3577469 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1793. Min Range: -6.1793
Max Act: 5.6168. Min Act: -0.1700
Data Index: 8136168 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #19