Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5334 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3071. Min Range: -8.3071
Max Act: 8.3071. Min Act: -0.1700
Data Index: 7431669 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3071. Min Range: -8.3071
Max Act: 8.1196. Min Act: -0.1700
Data Index: 3277130 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3071. Min Range: -8.3071
Max Act: 7.8071. Min Act: -0.1700
Data Index: 5703478 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3071. Min Range: -8.3071
Max Act: 7.8071. Min Act: -0.1700
Data Index: 3482570 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3071. Min Range: -8.3071
Max Act: 7.7446. Min Act: -0.1700
Data Index: 6172515 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3071. Min Range: -8.3071
Max Act: 7.7446. Min Act: -0.1700
Data Index: 3498290 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3071. Min Range: -8.3071
Max Act: 7.6821. Min Act: -0.1700
Data Index: 7283848 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3071. Min Range: -8.3071
Max Act: 7.6196. Min Act: -0.1700
Data Index: 4846589 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3071. Min Range: -8.3071
Max Act: 7.6196. Min Act: -0.1700
Data Index: 1880639 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3071. Min Range: -8.3071
Max Act: 7.5884. Min Act: -0.1700
Data Index: 6449972 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3071. Min Range: -8.3071
Max Act: 7.5571. Min Act: -0.1700
Data Index: 6969911 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3071. Min Range: -8.3071
Max Act: 7.4009. Min Act: -0.1700
Data Index: 8817804 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3071. Min Range: -8.3071
Max Act: 7.4321. Min Act: -0.1700
Data Index: 2512532 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3071. Min Range: -8.3071
Max Act: 7.3071. Min Act: -0.1700
Data Index: 6343536 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3071. Min Range: -8.3071
Max Act: 7.2759. Min Act: -0.1700
Data Index: 1891556 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3071. Min Range: -8.3071
Max Act: 7.2759. Min Act: -0.1700
Data Index: 5636981 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3071. Min Range: -8.3071
Max Act: 7.2759. Min Act: -0.1700
Data Index: 5350418 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3071. Min Range: -8.3071
Max Act: 7.2446. Min Act: -0.1700
Data Index: 6222080 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3071. Min Range: -8.3071
Max Act: 7.2446. Min Act: -0.1700
Data Index: 6740772 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3071. Min Range: -8.3071
Max Act: 7.2134. Min Act: -0.1700
Data Index: 2859642 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #19