Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 5061 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.1814. Min Range: -3.1814
Max Act: 3.1814. Min Act: -0.1700
Data Index: 3720967 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1814. Min Range: -3.1814
Max Act: 3.1499. Min Act: -0.1700
Data Index: 5403717 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1814. Min Range: -3.1814
Max Act: 3.1499. Min Act: -0.1700
Data Index: 2172012 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1814. Min Range: -3.1814
Max Act: 3.1342. Min Act: -0.1700
Data Index: 3335493 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1814. Min Range: -3.1814
Max Act: 3.1499. Min Act: -0.1700
Data Index: 6655013 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1814. Min Range: -3.1814
Max Act: 3.1026. Min Act: -0.1700
Data Index: 258588 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1814. Min Range: -3.1814
Max Act: 3.1026. Min Act: -0.1700
Data Index: 1118022 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1814. Min Range: -3.1814
Max Act: 3.0869. Min Act: -0.1700
Data Index: 5098465 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1814. Min Range: -3.1814
Max Act: 3.0711. Min Act: -0.1700
Data Index: 5711307 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1814. Min Range: -3.1814
Max Act: 3.0869. Min Act: -0.1700
Data Index: 616233 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1814. Min Range: -3.1814
Max Act: 3.0711. Min Act: -0.1700
Data Index: 6553695 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1814. Min Range: -3.1814
Max Act: 3.0711. Min Act: -0.1700
Data Index: 3744570 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1814. Min Range: -3.1814
Max Act: 3.0711. Min Act: -0.1700
Data Index: 2214557 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1814. Min Range: -3.1814
Max Act: 3.0553. Min Act: -0.1700
Data Index: 3723924 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1814. Min Range: -3.1814
Max Act: 3.0553. Min Act: -0.1700
Data Index: 6318557 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1814. Min Range: -3.1814
Max Act: 3.0711. Min Act: -0.1700
Data Index: 4032831 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1814. Min Range: -3.1814
Max Act: 3.0396. Min Act: -0.1700
Data Index: 3780532 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1814. Min Range: -3.1814
Max Act: 3.0238. Min Act: -0.1700
Data Index: 1024921 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1814. Min Range: -3.1814
Max Act: 3.0396. Min Act: -0.1700
Data Index: 5495564 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1814. Min Range: -3.1814
Max Act: 3.0396. Min Act: -0.1700
Data Index: 2552232 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19