Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3123 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.2926. Min Range: -8.2926
Max Act: 8.2926. Min Act: -0.1700
Data Index: 4402205 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2926. Min Range: -8.2926
Max Act: 8.2301. Min Act: -0.1700
Data Index: 1775553 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2926. Min Range: -8.2926
Max Act: 7.9801. Min Act: -0.1700
Data Index: 4023698 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2926. Min Range: -8.2926
Max Act: 7.7614. Min Act: -0.1700
Data Index: 306052 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2926. Min Range: -8.2926
Max Act: 7.5739. Min Act: -0.1700
Data Index: 4392627 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2926. Min Range: -8.2926
Max Act: 7.4801. Min Act: -0.1700
Data Index: 8685502 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2926. Min Range: -8.2926
Max Act: 7.4176. Min Act: -0.1700
Data Index: 8000289 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2926. Min Range: -8.2926
Max Act: 7.3864. Min Act: -0.1700
Data Index: 4891889 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2926. Min Range: -8.2926
Max Act: 7.3864. Min Act: -0.1700
Data Index: 5108300 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2926. Min Range: -8.2926
Max Act: 7.3864. Min Act: -0.1700
Data Index: 3981654 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2926. Min Range: -8.2926
Max Act: 7.3551. Min Act: -0.1700
Data Index: 8528105 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2926. Min Range: -8.2926
Max Act: 7.2926. Min Act: -0.1700
Data Index: 4189472 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2926. Min Range: -8.2926
Max Act: 7.2926. Min Act: -0.1700
Data Index: 1775557 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2926. Min Range: -8.2926
Max Act: 7.2301. Min Act: -0.1700
Data Index: 8530844 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2926. Min Range: -8.2926
Max Act: 7.1989. Min Act: -0.1700
Data Index: 3250216 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2926. Min Range: -8.2926
Max Act: 7.1989. Min Act: -0.1700
Data Index: 4209207 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2926. Min Range: -8.2926
Max Act: 7.2301. Min Act: -0.1700
Data Index: 4042480 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2926. Min Range: -8.2926
Max Act: 7.1364. Min Act: -0.1700
Data Index: 2422203 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2926. Min Range: -8.2926
Max Act: 7.1989. Min Act: -0.1700
Data Index: 8227105 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2926. Min Range: -8.2926
Max Act: 7.1676. Min Act: -0.1700
Data Index: 386617 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #19