Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1005 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.9540. Min Range: -2.9540
Max Act: 2.9540. Min Act: -0.1700
Data Index: 7144567 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9540. Min Range: -2.9540
Max Act: 2.8748. Min Act: -0.1700
Data Index: 1860845 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9540. Min Range: -2.9540
Max Act: 2.8589. Min Act: -0.1700
Data Index: 2301245 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9540. Min Range: -2.9540
Max Act: 2.8271. Min Act: -0.1700
Data Index: 7614718 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9540. Min Range: -2.9540
Max Act: 2.8112. Min Act: -0.1700
Data Index: 3123832 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9540. Min Range: -2.9540
Max Act: 2.7794. Min Act: -0.1700
Data Index: 8481060 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9540. Min Range: -2.9540
Max Act: 2.7794. Min Act: -0.1700
Data Index: 3105565 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9540. Min Range: -2.9540
Max Act: 2.7634. Min Act: -0.1700
Data Index: 3474790 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9540. Min Range: -2.9540
Max Act: 2.7475. Min Act: -0.1700
Data Index: 4063066 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9540. Min Range: -2.9540
Max Act: 2.7475. Min Act: -0.1700
Data Index: 2724198 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9540. Min Range: -2.9540
Max Act: 2.7634. Min Act: -0.1700
Data Index: 4980213 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9540. Min Range: -2.9540
Max Act: 2.7475. Min Act: -0.1700
Data Index: 3916266 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9540. Min Range: -2.9540
Max Act: 2.7315. Min Act: -0.1700
Data Index: 8278632 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9540. Min Range: -2.9540
Max Act: 2.7315. Min Act: -0.1700
Data Index: 6705234 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9540. Min Range: -2.9540
Max Act: 2.7315. Min Act: -0.1700
Data Index: 6375232 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9540. Min Range: -2.9540
Max Act: 2.7315. Min Act: -0.1700
Data Index: 3850629 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9540. Min Range: -2.9540
Max Act: 2.7155. Min Act: -0.1700
Data Index: 6128490 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9540. Min Range: -2.9540
Max Act: 2.7155. Min Act: -0.1700
Data Index: 7087609 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9540. Min Range: -2.9540
Max Act: 2.6995. Min Act: -0.1700
Data Index: 5004939 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9540. Min Range: -2.9540
Max Act: 2.6995. Min Act: -0.1700
Data Index: 649105 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #19