Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 758 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.7023. Min Range: -1.7023
Max Act: 1.7023. Min Act: -0.1695
Data Index: 1701675 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.7023. Min Range: -1.7023
Max Act: 1.6763. Min Act: -0.1700
Data Index: 3657010 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.7023. Min Range: -1.7023
Max Act: 1.6328. Min Act: -0.1691
Data Index: 3284339 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.7023. Min Range: -1.7023
Max Act: 1.6240. Min Act: -0.1694
Data Index: 404849 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.7023. Min Range: -1.7023
Max Act: 1.6240. Min Act: -0.1700
Data Index: 5642281 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.7023. Min Range: -1.7023
Max Act: 1.6066. Min Act: -0.1681
Data Index: 689907 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.7023. Min Range: -1.7023
Max Act: 1.5979. Min Act: -0.1700
Data Index: 3547422 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.7023. Min Range: -1.7023
Max Act: 1.6066. Min Act: -0.1700
Data Index: 3131033 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.7023. Min Range: -1.7023
Max Act: 1.5891. Min Act: -0.1700
Data Index: 3284340 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.7023. Min Range: -1.7023
Max Act: 1.5804. Min Act: -0.1700
Data Index: 3131034 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.7023. Min Range: -1.7023
Max Act: 1.5891. Min Act: -0.1700
Data Index: 5642280 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.7023. Min Range: -1.7023
Max Act: 1.5716. Min Act: -0.1700
Data Index: 8237915 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.7023. Min Range: -1.7023
Max Act: 1.5716. Min Act: -0.1700
Data Index: 4705834 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.7023. Min Range: -1.7023
Max Act: 1.5716. Min Act: -0.1696
Data Index: 8422361 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.7023. Min Range: -1.7023
Max Act: 1.5629. Min Act: -0.1700
Data Index: 5581645 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.7023. Min Range: -1.7023
Max Act: 1.5716. Min Act: -0.1700
Data Index: 7148689 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.7023. Min Range: -1.7023
Max Act: 1.5541. Min Act: -0.1698
Data Index: 5819612 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.7023. Min Range: -1.7023
Max Act: 1.5454. Min Act: -0.1700
Data Index: 122159 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.7023. Min Range: -1.7023
Max Act: 1.5541. Min Act: -0.1696
Data Index: 5716228 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.7023. Min Range: -1.7023
Max Act: 1.5454. Min Act: -0.1700
Data Index: 3604243 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #19