Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2860 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1374. Min Range: -5.1374
Max Act: 5.1374. Min Act: -0.1700
Data Index: 8557978 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1374. Min Range: -5.1374
Max Act: 5.1061. Min Act: -0.1700
Data Index: 3250222 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1374. Min Range: -5.1374
Max Act: 5.0749. Min Act: -0.1700
Data Index: 3619360 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1374. Min Range: -5.1374
Max Act: 5.0124. Min Act: -0.1700
Data Index: 1853890 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1374. Min Range: -5.1374
Max Act: 4.8561. Min Act: -0.1700
Data Index: 7844847 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1374. Min Range: -5.1374
Max Act: 4.7624. Min Act: -0.1700
Data Index: 5606693 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1374. Min Range: -5.1374
Max Act: 4.7624. Min Act: -0.1700
Data Index: 3639275 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1374. Min Range: -5.1374
Max Act: 4.7311. Min Act: -0.1700
Data Index: 419646 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1374. Min Range: -5.1374
Max Act: 4.7624. Min Act: -0.1700
Data Index: 8391759 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1374. Min Range: -5.1374
Max Act: 4.7624. Min Act: -0.1700
Data Index: 397283 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1374. Min Range: -5.1374
Max Act: 4.6999. Min Act: -0.1700
Data Index: 1536064 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1374. Min Range: -5.1374
Max Act: 4.7311. Min Act: -0.1700
Data Index: 6189946 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1374. Min Range: -5.1374
Max Act: 4.6686. Min Act: -0.1700
Data Index: 4746346 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1374. Min Range: -5.1374
Max Act: 4.6686. Min Act: -0.1700
Data Index: 6515067 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1374. Min Range: -5.1374
Max Act: 4.6374. Min Act: -0.1700
Data Index: 752505 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1374. Min Range: -5.1374
Max Act: 4.6374. Min Act: -0.1700
Data Index: 3893445 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1374. Min Range: -5.1374
Max Act: 4.6374. Min Act: -0.1700
Data Index: 4666110 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1374. Min Range: -5.1374
Max Act: 4.6061. Min Act: -0.1700
Data Index: 5982578 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1374. Min Range: -5.1374
Max Act: 4.6061. Min Act: -0.1700
Data Index: 2023304 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1374. Min Range: -5.1374
Max Act: 4.6061. Min Act: -0.1700
Data Index: 652914 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #19