Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3483 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5588. Min Range: -7.5588
Max Act: 7.5588. Min Act: -0.1700
Data Index: 5215101 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5588. Min Range: -7.5588
Max Act: 7.3401. Min Act: -0.1700
Data Index: 5391605 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5588. Min Range: -7.5588
Max Act: 7.3088. Min Act: -0.1700
Data Index: 8050468 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5588. Min Range: -7.5588
Max Act: 7.2151. Min Act: -0.1700
Data Index: 3012878 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5588. Min Range: -7.5588
Max Act: 7.2463. Min Act: -0.1700
Data Index: 5152432 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5588. Min Range: -7.5588
Max Act: 7.1838. Min Act: -0.1700
Data Index: 4191940 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5588. Min Range: -7.5588
Max Act: 7.1838. Min Act: -0.1700
Data Index: 5743431 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5588. Min Range: -7.5588
Max Act: 7.2151. Min Act: -0.1700
Data Index: 5215102 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5588. Min Range: -7.5588
Max Act: 7.1526. Min Act: -0.1700
Data Index: 3599137 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5588. Min Range: -7.5588
Max Act: 7.1213. Min Act: -0.1700
Data Index: 6267972 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5588. Min Range: -7.5588
Max Act: 7.0901. Min Act: -0.1700
Data Index: 5347800 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5588. Min Range: -7.5588
Max Act: 7.0588. Min Act: -0.1700
Data Index: 6913449 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5588. Min Range: -7.5588
Max Act: 7.0276. Min Act: -0.1700
Data Index: 4718016 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5588. Min Range: -7.5588
Max Act: 7.0276. Min Act: -0.1700
Data Index: 4620691 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5588. Min Range: -7.5588
Max Act: 6.9963. Min Act: -0.1700
Data Index: 7601518 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5588. Min Range: -7.5588
Max Act: 6.9963. Min Act: -0.1700
Data Index: 3598449 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5588. Min Range: -7.5588
Max Act: 6.9963. Min Act: -0.1700
Data Index: 6007305 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5588. Min Range: -7.5588
Max Act: 6.9963. Min Act: -0.1700
Data Index: 1289803 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5588. Min Range: -7.5588
Max Act: 6.9651. Min Act: -0.1700
Data Index: 4070254 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5588. Min Range: -7.5588
Max Act: 6.9651. Min Act: -0.1700
Data Index: 7816053 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #19