Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 552 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.9016. Min Range: -5.9016
Max Act: 5.9016. Min Act: -0.1700
Data Index: 7615634 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9016. Min Range: -5.9016
Max Act: 5.7141. Min Act: -0.1700
Data Index: 25969 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9016. Min Range: -5.9016
Max Act: 5.6829. Min Act: -0.1700
Data Index: 4763992 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9016. Min Range: -5.9016
Max Act: 5.6204. Min Act: -0.1700
Data Index: 3302907 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9016. Min Range: -5.9016
Max Act: 5.5891. Min Act: -0.1700
Data Index: 8580350 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9016. Min Range: -5.9016
Max Act: 5.5579. Min Act: -0.1700
Data Index: 7432592 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9016. Min Range: -5.9016
Max Act: 5.6204. Min Act: -0.1700
Data Index: 1324281 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9016. Min Range: -5.9016
Max Act: 5.5579. Min Act: -0.1700
Data Index: 1353950 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9016. Min Range: -5.9016
Max Act: 5.5579. Min Act: -0.1700
Data Index: 6962794 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9016. Min Range: -5.9016
Max Act: 5.5579. Min Act: -0.1700
Data Index: 7772789 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9016. Min Range: -5.9016
Max Act: 5.4954. Min Act: -0.1700
Data Index: 4350483 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9016. Min Range: -5.9016
Max Act: 5.4954. Min Act: -0.1700
Data Index: 3709764 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9016. Min Range: -5.9016
Max Act: 5.4641. Min Act: -0.1700
Data Index: 5816836 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9016. Min Range: -5.9016
Max Act: 5.4329. Min Act: -0.1700
Data Index: 3777918 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9016. Min Range: -5.9016
Max Act: 5.4641. Min Act: -0.1700
Data Index: 6026033 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9016. Min Range: -5.9016
Max Act: 5.4016. Min Act: -0.1700
Data Index: 1680769 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9016. Min Range: -5.9016
Max Act: 5.4016. Min Act: -0.1700
Data Index: 3894066 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9016. Min Range: -5.9016
Max Act: 5.3704. Min Act: -0.1700
Data Index: 5452279 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9016. Min Range: -5.9016
Max Act: 5.3704. Min Act: -0.1700
Data Index: 4400479 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9016. Min Range: -5.9016
Max Act: 5.3704. Min Act: -0.1700
Data Index: 8039211 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #19