Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4026 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.5588. Min Range: -9.5588
Max Act: 9.4963. Min Act: -0.1700
Data Index: 7309563 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.5588. Min Range: -9.5588
Max Act: 9.5588. Min Act: -0.1700
Data Index: 2965083 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.5588. Min Range: -9.5588
Max Act: 9.5588. Min Act: -0.1700
Data Index: 792100 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.5588. Min Range: -9.5588
Max Act: 9.4338. Min Act: -0.1700
Data Index: 4388785 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.5588. Min Range: -9.5588
Max Act: 9.3713. Min Act: -0.1700
Data Index: 5366508 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.5588. Min Range: -9.5588
Max Act: 9.3088. Min Act: -0.1700
Data Index: 215352 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.5588. Min Range: -9.5588
Max Act: 9.2463. Min Act: -0.1700
Data Index: 5999270 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.5588. Min Range: -9.5588
Max Act: 9.1838. Min Act: -0.1700
Data Index: 491292 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.5588. Min Range: -9.5588
Max Act: 9.0588. Min Act: -0.1700
Data Index: 52737 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.5588. Min Range: -9.5588
Max Act: 9.1213. Min Act: -0.1700
Data Index: 1597653 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.5588. Min Range: -9.5588
Max Act: 9.1213. Min Act: -0.1700
Data Index: 6459007 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.5588. Min Range: -9.5588
Max Act: 9.1213. Min Act: -0.1700
Data Index: 4787743 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.5588. Min Range: -9.5588
Max Act: 9.0588. Min Act: -0.1700
Data Index: 7114345 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.5588. Min Range: -9.5588
Max Act: 9.0588. Min Act: -0.1700
Data Index: 7126867 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.5588. Min Range: -9.5588
Max Act: 9.0588. Min Act: -0.1700
Data Index: 224421 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.5588. Min Range: -9.5588
Max Act: 8.9963. Min Act: -0.1700
Data Index: 3527718 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.5588. Min Range: -9.5588
Max Act: 8.9963. Min Act: -0.1700
Data Index: 6762806 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.5588. Min Range: -9.5588
Max Act: 8.9963. Min Act: -0.1700
Data Index: 8455065 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.5588. Min Range: -9.5588
Max Act: 8.9338. Min Act: -0.1700
Data Index: 1702155 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.5588. Min Range: -9.5588
Max Act: 8.9338. Min Act: -0.1700
Data Index: 436649 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #19