Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 972 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9390. Min Range: -5.9390
Max Act: 5.9390. Min Act: -0.1700
Data Index: 4475474 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9390. Min Range: -5.9390
Max Act: 5.8140. Min Act: -0.1700
Data Index: 3295799 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9390. Min Range: -5.9390
Max Act: 5.7202. Min Act: -0.1700
Data Index: 6073008 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9390. Min Range: -5.9390
Max Act: 5.7202. Min Act: -0.1700
Data Index: 5787733 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9390. Min Range: -5.9390
Max Act: 5.7515. Min Act: -0.1700
Data Index: 3043666 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9390. Min Range: -5.9390
Max Act: 5.6890. Min Act: -0.1700
Data Index: 6073013 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9390. Min Range: -5.9390
Max Act: 5.6577. Min Act: -0.1700
Data Index: 3043664 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9390. Min Range: -5.9390
Max Act: 5.5952. Min Act: -0.1700
Data Index: 655012 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9390. Min Range: -5.9390
Max Act: 5.5952. Min Act: -0.1700
Data Index: 655008 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9390. Min Range: -5.9390
Max Act: 5.5640. Min Act: -0.1700
Data Index: 2109822 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9390. Min Range: -5.9390
Max Act: 5.5640. Min Act: -0.1700
Data Index: 4428553 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9390. Min Range: -5.9390
Max Act: 5.5640. Min Act: -0.1700
Data Index: 6073016 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9390. Min Range: -5.9390
Max Act: 5.4390. Min Act: -0.1700
Data Index: 657978 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9390. Min Range: -5.9390
Max Act: 5.4390. Min Act: -0.1700
Data Index: 4454568 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9390. Min Range: -5.9390
Max Act: 5.4390. Min Act: -0.1700
Data Index: 2067004 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9390. Min Range: -5.9390
Max Act: 5.4077. Min Act: -0.1700
Data Index: 4265305 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9390. Min Range: -5.9390
Max Act: 5.4077. Min Act: -0.1700
Data Index: 6788473 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9390. Min Range: -5.9390
Max Act: 5.4077. Min Act: -0.1700
Data Index: 6073017 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9390. Min Range: -5.9390
Max Act: 5.4077. Min Act: -0.1700
Data Index: 214795 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9390. Min Range: -5.9390
Max Act: 5.3765. Min Act: -0.1700
Data Index: 5729580 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #19