Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2771 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0409. Min Range: -7.0409
Max Act: 7.0409. Min Act: -0.1700
Data Index: 4384820 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0409. Min Range: -7.0409
Max Act: 6.7909. Min Act: -0.1700
Data Index: 2071260 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0409. Min Range: -7.0409
Max Act: 6.7284. Min Act: -0.1700
Data Index: 5065919 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0409. Min Range: -7.0409
Max Act: 6.7284. Min Act: -0.1700
Data Index: 6362416 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0409. Min Range: -7.0409
Max Act: 6.7284. Min Act: -0.1700
Data Index: 2416798 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0409. Min Range: -7.0409
Max Act: 6.6659. Min Act: -0.1700
Data Index: 8754502 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0409. Min Range: -7.0409
Max Act: 6.6659. Min Act: -0.1700
Data Index: 1890221 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0409. Min Range: -7.0409
Max Act: 6.6659. Min Act: -0.1700
Data Index: 7979590 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0409. Min Range: -7.0409
Max Act: 6.6346. Min Act: -0.1700
Data Index: 7871203 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0409. Min Range: -7.0409
Max Act: 6.6346. Min Act: -0.1700
Data Index: 3600010 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0409. Min Range: -7.0409
Max Act: 6.6034. Min Act: -0.1700
Data Index: 1434092 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0409. Min Range: -7.0409
Max Act: 6.5721. Min Act: -0.1700
Data Index: 3451518 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0409. Min Range: -7.0409
Max Act: 6.5409. Min Act: -0.1700
Data Index: 2590683 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0409. Min Range: -7.0409
Max Act: 6.5721. Min Act: -0.1700
Data Index: 2148851 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0409. Min Range: -7.0409
Max Act: 6.5721. Min Act: -0.1700
Data Index: 3428202 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0409. Min Range: -7.0409
Max Act: 6.5409. Min Act: -0.1700
Data Index: 694056 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0409. Min Range: -7.0409
Max Act: 6.5721. Min Act: -0.1700
Data Index: 6000500 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0409. Min Range: -7.0409
Max Act: 6.5409. Min Act: -0.1700
Data Index: 21029 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0409. Min Range: -7.0409
Max Act: 6.5409. Min Act: -0.1700
Data Index: 5949111 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0409. Min Range: -7.0409
Max Act: 6.5409. Min Act: -0.1700
Data Index: 8156625 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #19