Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2593 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.1622. Min Range: -6.1622
Max Act: 6.1622. Min Act: -0.1700
Data Index: 964323 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1622. Min Range: -6.1622
Max Act: 6.0684. Min Act: -0.1700
Data Index: 7678962 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1622. Min Range: -6.1622
Max Act: 5.9122. Min Act: -0.1700
Data Index: 7386325 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1622. Min Range: -6.1622
Max Act: 5.8497. Min Act: -0.1700
Data Index: 5269604 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1622. Min Range: -6.1622
Max Act: 5.8497. Min Act: -0.1700
Data Index: 6575398 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1622. Min Range: -6.1622
Max Act: 5.8497. Min Act: -0.1700
Data Index: 6923865 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1622. Min Range: -6.1622
Max Act: 5.8497. Min Act: -0.1700
Data Index: 7771450 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1622. Min Range: -6.1622
Max Act: 5.8184. Min Act: -0.1700
Data Index: 6272426 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1622. Min Range: -6.1622
Max Act: 5.7872. Min Act: -0.1700
Data Index: 5912838 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1622. Min Range: -6.1622
Max Act: 5.8184. Min Act: -0.1700
Data Index: 7249976 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1622. Min Range: -6.1622
Max Act: 5.7872. Min Act: -0.1700
Data Index: 6431129 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1622. Min Range: -6.1622
Max Act: 5.7559. Min Act: -0.1700
Data Index: 1180316 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1622. Min Range: -6.1622
Max Act: 5.7559. Min Act: -0.1700
Data Index: 8219592 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1622. Min Range: -6.1622
Max Act: 5.7247. Min Act: -0.1700
Data Index: 7249975 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1622. Min Range: -6.1622
Max Act: 5.6934. Min Act: -0.1700
Data Index: 2998808 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1622. Min Range: -6.1622
Max Act: 5.6934. Min Act: -0.1700
Data Index: 848232 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1622. Min Range: -6.1622
Max Act: 5.6622. Min Act: -0.1700
Data Index: 496619 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1622. Min Range: -6.1622
Max Act: 5.6934. Min Act: -0.1700
Data Index: 940757 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1622. Min Range: -6.1622
Max Act: 5.6309. Min Act: -0.1700
Data Index: 1034416 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1622. Min Range: -6.1622
Max Act: 5.6622. Min Act: -0.1700
Data Index: 4584931 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #19