Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4137 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.2704. Min Range: -10.2704
Max Act: 10.2704. Min Act: -0.1700
Data Index: 4580061 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.2704. Min Range: -10.2704
Max Act: 9.8329. Min Act: -0.1700
Data Index: 3599994 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.2704. Min Range: -10.2704
Max Act: 9.8329. Min Act: -0.1700
Data Index: 38711 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.2704. Min Range: -10.2704
Max Act: 9.7704. Min Act: -0.1700
Data Index: 342586 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.2704. Min Range: -10.2704
Max Act: 9.7704. Min Act: -0.1700
Data Index: 4497196 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.2704. Min Range: -10.2704
Max Act: 9.7079. Min Act: -0.1700
Data Index: 1672632 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.2704. Min Range: -10.2704
Max Act: 9.6454. Min Act: -0.1700
Data Index: 7350561 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.2704. Min Range: -10.2704
Max Act: 9.6454. Min Act: -0.1700
Data Index: 4020218 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.2704. Min Range: -10.2704
Max Act: 9.5204. Min Act: -0.1700
Data Index: 8256893 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.2704. Min Range: -10.2704
Max Act: 9.5204. Min Act: -0.1700
Data Index: 4437010 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.2704. Min Range: -10.2704
Max Act: 9.5204. Min Act: -0.1700
Data Index: 8429259 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.2704. Min Range: -10.2704
Max Act: 9.5204. Min Act: -0.1700
Data Index: 689527 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.2704. Min Range: -10.2704
Max Act: 9.5204. Min Act: -0.1700
Data Index: 6092217 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.2704. Min Range: -10.2704
Max Act: 9.5204. Min Act: -0.1700
Data Index: 4204090 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.2704. Min Range: -10.2704
Max Act: 9.4579. Min Act: -0.1700
Data Index: 4727117 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.2704. Min Range: -10.2704
Max Act: 9.4579. Min Act: -0.1700
Data Index: 7350568 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.2704. Min Range: -10.2704
Max Act: 9.4579. Min Act: -0.1700
Data Index: 4215403 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.2704. Min Range: -10.2704
Max Act: 9.4579. Min Act: -0.1700
Data Index: 3742176 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.2704. Min Range: -10.2704
Max Act: 9.4579. Min Act: -0.1700
Data Index: 4658256 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.2704. Min Range: -10.2704
Max Act: 9.3954. Min Act: -0.1700
Data Index: 5965707 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #19