Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 866 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.5486. Min Range: -1.5486
Max Act: 1.5486. Min Act: -0.1700
Data Index: 4099767 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.5486. Min Range: -1.5486
Max Act: 1.5486. Min Act: -0.1700
Data Index: 4648097 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.5486. Min Range: -1.5486
Max Act: 1.4960. Min Act: -0.1700
Data Index: 5878033 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.5486. Min Range: -1.5486
Max Act: 1.4608. Min Act: -0.1700
Data Index: 1804176 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.5486. Min Range: -1.5486
Max Act: 1.4784. Min Act: -0.1700
Data Index: 5809217 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.5486. Min Range: -1.5486
Max Act: 1.4608. Min Act: -0.1700
Data Index: 7487404 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.5486. Min Range: -1.5486
Max Act: 1.4608. Min Act: -0.1700
Data Index: 3473255 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.5486. Min Range: -1.5486
Max Act: 1.4257. Min Act: -0.1700
Data Index: 4966203 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.5486. Min Range: -1.5486
Max Act: 1.4608. Min Act: -0.1700
Data Index: 2080034 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.5486. Min Range: -1.5486
Max Act: 1.4433. Min Act: -0.1700
Data Index: 5053219 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.5486. Min Range: -1.5486
Max Act: 1.4080. Min Act: -0.1700
Data Index: 8815990 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.5486. Min Range: -1.5486
Max Act: 1.4257. Min Act: -0.1700
Data Index: 3570553 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.5486. Min Range: -1.5486
Max Act: 1.4257. Min Act: -0.1700
Data Index: 4268352 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.5486. Min Range: -1.5486
Max Act: 1.4080. Min Act: -0.1700
Data Index: 5622455 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.5486. Min Range: -1.5486
Max Act: 1.4080. Min Act: -0.1700
Data Index: 3255940 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.5486. Min Range: -1.5486
Max Act: 1.4080. Min Act: -0.1700
Data Index: 1590030 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.5486. Min Range: -1.5486
Max Act: 1.4080. Min Act: -0.1700
Data Index: 1306323 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.5486. Min Range: -1.5486
Max Act: 1.4080. Min Act: -0.1700
Data Index: 2592906 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.5486. Min Range: -1.5486
Max Act: 1.4080. Min Act: -0.1700
Data Index: 6897749 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.5486. Min Range: -1.5486
Max Act: 1.3904. Min Act: -0.1700
Data Index: 7086940 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19