Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3029 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 1.5668. Min Range: -1.5668
Max Act: 1.5668. Min Act: -0.1700
Data Index: 6173044 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.5668. Min Range: -1.5668
Max Act: 1.5581. Min Act: -0.1700
Data Index: 2916699 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.5668. Min Range: -1.5668
Max Act: 1.5493. Min Act: -0.1700
Data Index: 4031760 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.5668. Min Range: -1.5668
Max Act: 1.5406. Min Act: -0.1700
Data Index: 6618697 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.5668. Min Range: -1.5668
Max Act: 1.5318. Min Act: -0.1700
Data Index: 6097324 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.5668. Min Range: -1.5668
Max Act: 1.5231. Min Act: -0.1700
Data Index: 4610473 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.5668. Min Range: -1.5668
Max Act: 1.5143. Min Act: -0.1700
Data Index: 8164000 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.5668. Min Range: -1.5668
Max Act: 1.5143. Min Act: -0.1700
Data Index: 742145 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.5668. Min Range: -1.5668
Max Act: 1.5143. Min Act: -0.1700
Data Index: 5851669 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.5668. Min Range: -1.5668
Max Act: 1.5143. Min Act: -0.1700
Data Index: 2371765 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.5668. Min Range: -1.5668
Max Act: 1.5055. Min Act: -0.1700
Data Index: 8168021 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.5668. Min Range: -1.5668
Max Act: 1.5231. Min Act: -0.1700
Data Index: 4042599 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.5668. Min Range: -1.5668
Max Act: 1.5143. Min Act: -0.1700
Data Index: 357892 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.5668. Min Range: -1.5668
Max Act: 1.5143. Min Act: -0.1700
Data Index: 2228760 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.5668. Min Range: -1.5668
Max Act: 1.5143. Min Act: -0.1700
Data Index: 1522055 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.5668. Min Range: -1.5668
Max Act: 1.5143. Min Act: -0.1700
Data Index: 6800471 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.5668. Min Range: -1.5668
Max Act: 1.5055. Min Act: -0.1700
Data Index: 298391 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.5668. Min Range: -1.5668
Max Act: 1.5055. Min Act: -0.1700
Data Index: 351083 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.5668. Min Range: -1.5668
Max Act: 1.5055. Min Act: -0.1700
Data Index: 2188043 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.5668. Min Range: -1.5668
Max Act: 1.5055. Min Act: -0.1700
Data Index: 1960215 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19