Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1632 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.6770. Min Range: -3.6770
Max Act: 3.6770. Min Act: -0.1700
Data Index: 6348772 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6770. Min Range: -3.6770
Max Act: 3.6613. Min Act: -0.1700
Data Index: 3676683 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6770. Min Range: -3.6770
Max Act: 3.6300. Min Act: -0.1700
Data Index: 2477058 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6770. Min Range: -3.6770
Max Act: 3.6144. Min Act: -0.1700
Data Index: 2151290 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6770. Min Range: -3.6770
Max Act: 3.6144. Min Act: -0.1700
Data Index: 3046167 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6770. Min Range: -3.6770
Max Act: 3.5674. Min Act: -0.1700
Data Index: 6313756 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6770. Min Range: -3.6770
Max Act: 3.5518. Min Act: -0.1700
Data Index: 7307779 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6770. Min Range: -3.6770
Max Act: 3.5518. Min Act: -0.1700
Data Index: 8727669 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6770. Min Range: -3.6770
Max Act: 3.5204. Min Act: -0.1700
Data Index: 5371701 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6770. Min Range: -3.6770
Max Act: 3.5361. Min Act: -0.1700
Data Index: 4915217 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6770. Min Range: -3.6770
Max Act: 3.5204. Min Act: -0.1700
Data Index: 1005380 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6770. Min Range: -3.6770
Max Act: 3.5048. Min Act: -0.1700
Data Index: 883773 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6770. Min Range: -3.6770
Max Act: 3.4891. Min Act: -0.1700
Data Index: 5629330 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6770. Min Range: -3.6770
Max Act: 3.4891. Min Act: -0.1700
Data Index: 5810825 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6770. Min Range: -3.6770
Max Act: 3.4891. Min Act: -0.1700
Data Index: 6714791 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6770. Min Range: -3.6770
Max Act: 3.4891. Min Act: -0.1700
Data Index: 5992976 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6770. Min Range: -3.6770
Max Act: 3.4735. Min Act: -0.1700
Data Index: 4645111 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6770. Min Range: -3.6770
Max Act: 3.4578. Min Act: -0.1700
Data Index: 8161780 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6770. Min Range: -3.6770
Max Act: 3.4891. Min Act: -0.1700
Data Index: 359140 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6770. Min Range: -3.6770
Max Act: 3.4735. Min Act: -0.1700
Data Index: 2483946 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #19