Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 627 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.3788. Min Range: -2.3788
Max Act: 2.3788. Min Act: -0.1700
Data Index: 8691957 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3788. Min Range: -2.3788
Max Act: 2.3625. Min Act: -0.1700
Data Index: 423029 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3788. Min Range: -2.3788
Max Act: 2.3788. Min Act: -0.1700
Data Index: 3089865 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3788. Min Range: -2.3788
Max Act: 2.3625. Min Act: -0.1700
Data Index: 4619331 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3788. Min Range: -2.3788
Max Act: 2.3461. Min Act: -0.1700
Data Index: 7606239 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3788. Min Range: -2.3788
Max Act: 2.3297. Min Act: -0.1700
Data Index: 5681441 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3788. Min Range: -2.3788
Max Act: 2.3461. Min Act: -0.1700
Data Index: 1089635 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3788. Min Range: -2.3788
Max Act: 2.3133. Min Act: -0.1700
Data Index: 6858566 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3788. Min Range: -2.3788
Max Act: 2.3297. Min Act: -0.1700
Data Index: 2411096 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3788. Min Range: -2.3788
Max Act: 2.3133. Min Act: -0.1700
Data Index: 4829258 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3788. Min Range: -2.3788
Max Act: 2.2804. Min Act: -0.1700
Data Index: 5197667 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3788. Min Range: -2.3788
Max Act: 2.2804. Min Act: -0.1700
Data Index: 7252753 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3788. Min Range: -2.3788
Max Act: 2.2804. Min Act: -0.1700
Data Index: 6451198 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3788. Min Range: -2.3788
Max Act: 2.2804. Min Act: -0.1700
Data Index: 1752520 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3788. Min Range: -2.3788
Max Act: 2.2968. Min Act: -0.1700
Data Index: 4269697 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3788. Min Range: -2.3788
Max Act: 2.2639. Min Act: -0.1700
Data Index: 7457692 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3788. Min Range: -2.3788
Max Act: 2.2968. Min Act: -0.1700
Data Index: 6275191 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3788. Min Range: -2.3788
Max Act: 2.2968. Min Act: -0.1700
Data Index: 4232712 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3788. Min Range: -2.3788
Max Act: 2.2639. Min Act: -0.1700
Data Index: 6820572 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3788. Min Range: -2.3788
Max Act: 2.2804. Min Act: -0.1700
Data Index: 2041507 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #19