Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1921 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.4551. Min Range: -5.4551
Max Act: 5.4551. Min Act: -0.1700
Data Index: 2023775 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4551. Min Range: -5.4551
Max Act: 5.3926. Min Act: -0.1700
Data Index: 2043371 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4551. Min Range: -5.4551
Max Act: 5.2989. Min Act: -0.1700
Data Index: 2957140 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4551. Min Range: -5.4551
Max Act: 5.2676. Min Act: -0.1700
Data Index: 6436530 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4551. Min Range: -5.4551
Max Act: 5.2051. Min Act: -0.1700
Data Index: 3199706 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4551. Min Range: -5.4551
Max Act: 5.1739. Min Act: -0.1700
Data Index: 3995675 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4551. Min Range: -5.4551
Max Act: 5.1114. Min Act: -0.1700
Data Index: 5829951 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4551. Min Range: -5.4551
Max Act: 5.1426. Min Act: -0.1700
Data Index: 6880175 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4551. Min Range: -5.4551
Max Act: 5.1426. Min Act: -0.1700
Data Index: 1875839 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4551. Min Range: -5.4551
Max Act: 5.1114. Min Act: -0.1700
Data Index: 6911202 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4551. Min Range: -5.4551
Max Act: 5.0489. Min Act: -0.1700
Data Index: 3742138 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4551. Min Range: -5.4551
Max Act: 5.0489. Min Act: -0.1700
Data Index: 3758275 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4551. Min Range: -5.4551
Max Act: 5.0489. Min Act: -0.1700
Data Index: 2940883 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4551. Min Range: -5.4551
Max Act: 5.0801. Min Act: -0.1700
Data Index: 3314891 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4551. Min Range: -5.4551
Max Act: 5.0489. Min Act: -0.1700
Data Index: 3544383 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4551. Min Range: -5.4551
Max Act: 5.0489. Min Act: -0.1700
Data Index: 319834 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4551. Min Range: -5.4551
Max Act: 4.9864. Min Act: -0.1700
Data Index: 5895189 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4551. Min Range: -5.4551
Max Act: 4.9864. Min Act: -0.1700
Data Index: 1231315 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4551. Min Range: -5.4551
Max Act: 4.9864. Min Act: -0.1700
Data Index: 161781 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4551. Min Range: -5.4551
Max Act: 4.9864. Min Act: -0.1700
Data Index: 4039364 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #19