Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5017 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1702. Min Range: -7.1702
Max Act: 7.1702. Min Act: -0.1700
Data Index: 107046 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1702. Min Range: -7.1702
Max Act: 6.6077. Min Act: -0.1700
Data Index: 6658591 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1702. Min Range: -7.1702
Max Act: 6.5765. Min Act: -0.1700
Data Index: 8799402 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1702. Min Range: -7.1702
Max Act: 6.5452. Min Act: -0.1700
Data Index: 7421825 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1702. Min Range: -7.1702
Max Act: 6.4202. Min Act: -0.1700
Data Index: 485503 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1702. Min Range: -7.1702
Max Act: 6.3265. Min Act: -0.1700
Data Index: 2438499 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1702. Min Range: -7.1702
Max Act: 6.3265. Min Act: -0.1700
Data Index: 8678505 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1702. Min Range: -7.1702
Max Act: 6.2952. Min Act: -0.1700
Data Index: 1429321 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1702. Min Range: -7.1702
Max Act: 6.2640. Min Act: -0.1700
Data Index: 922094 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1702. Min Range: -7.1702
Max Act: 6.2015. Min Act: -0.1700
Data Index: 1887814 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1702. Min Range: -7.1702
Max Act: 6.2015. Min Act: -0.1700
Data Index: 4155581 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1702. Min Range: -7.1702
Max Act: 6.1702. Min Act: -0.1700
Data Index: 1219878 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1702. Min Range: -7.1702
Max Act: 6.1390. Min Act: -0.1700
Data Index: 2296613 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1702. Min Range: -7.1702
Max Act: 6.1390. Min Act: -0.1700
Data Index: 6180379 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1702. Min Range: -7.1702
Max Act: 6.1390. Min Act: -0.1700
Data Index: 1482184 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1702. Min Range: -7.1702
Max Act: 6.1390. Min Act: -0.1700
Data Index: 4600667 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1702. Min Range: -7.1702
Max Act: 6.1390. Min Act: -0.1700
Data Index: 3591578 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1702. Min Range: -7.1702
Max Act: 6.1077. Min Act: -0.1700
Data Index: 3732502 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1702. Min Range: -7.1702
Max Act: 6.1077. Min Act: -0.1700
Data Index: 6848920 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1702. Min Range: -7.1702
Max Act: 6.0765. Min Act: -0.1700
Data Index: 2895407 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #19