Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3449 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.8778. Min Range: -3.8778
Max Act: 3.8778. Min Act: -0.1700
Data Index: 5582504 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8778. Min Range: -3.8778
Max Act: 3.7370. Min Act: -0.1700
Data Index: 3999774 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8778. Min Range: -3.8778
Max Act: 3.6588. Min Act: -0.1700
Data Index: 7335328 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8778. Min Range: -3.8778
Max Act: 3.6901. Min Act: -0.1700
Data Index: 6771654 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8778. Min Range: -3.8778
Max Act: 3.6901. Min Act: -0.1700
Data Index: 3526949 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8778. Min Range: -3.8778
Max Act: 3.5806. Min Act: -0.1700
Data Index: 184530 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8778. Min Range: -3.8778
Max Act: 3.5962. Min Act: -0.1700
Data Index: 4213736 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8778. Min Range: -3.8778
Max Act: 3.5806. Min Act: -0.1700
Data Index: 1373400 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8778. Min Range: -3.8778
Max Act: 3.5806. Min Act: -0.1700
Data Index: 5564542 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8778. Min Range: -3.8778
Max Act: 3.5806. Min Act: -0.1700
Data Index: 5144032 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8778. Min Range: -3.8778
Max Act: 3.5023. Min Act: -0.1700
Data Index: 1371910 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8778. Min Range: -3.8778
Max Act: 3.4866. Min Act: -0.1700
Data Index: 3583212 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8778. Min Range: -3.8778
Max Act: 3.4866. Min Act: -0.1700
Data Index: 77917 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8778. Min Range: -3.8778
Max Act: 3.4553. Min Act: -0.1700
Data Index: 4811961 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8778. Min Range: -3.8778
Max Act: 3.4240. Min Act: -0.1700
Data Index: 3736668 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8778. Min Range: -3.8778
Max Act: 3.4553. Min Act: -0.1700
Data Index: 6455658 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8778. Min Range: -3.8778
Max Act: 3.4710. Min Act: -0.1700
Data Index: 3553927 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8778. Min Range: -3.8778
Max Act: 3.4710. Min Act: -0.1700
Data Index: 8299080 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8778. Min Range: -3.8778
Max Act: 3.4553. Min Act: -0.1700
Data Index: 3903674 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8778. Min Range: -3.8778
Max Act: 3.4396. Min Act: -0.1700
Data Index: 3884355 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #19