Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2866 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.2022. Min Range: -5.2022
Max Act: 5.2022. Min Act: -0.1700
Data Index: 8322948 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2022. Min Range: -5.2022
Max Act: 5.0459. Min Act: -0.1700
Data Index: 8043950 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2022. Min Range: -5.2022
Max Act: 5.0459. Min Act: -0.1700
Data Index: 7298778 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2022. Min Range: -5.2022
Max Act: 4.9209. Min Act: -0.1700
Data Index: 940275 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2022. Min Range: -5.2022
Max Act: 4.8897. Min Act: -0.1700
Data Index: 8301397 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2022. Min Range: -5.2022
Max Act: 4.9522. Min Act: -0.1700
Data Index: 4010850 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2022. Min Range: -5.2022
Max Act: 4.8897. Min Act: -0.1700
Data Index: 4695541 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2022. Min Range: -5.2022
Max Act: 4.8897. Min Act: -0.1700
Data Index: 3788855 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2022. Min Range: -5.2022
Max Act: 4.8584. Min Act: -0.1700
Data Index: 3859745 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2022. Min Range: -5.2022
Max Act: 4.8584. Min Act: -0.1700
Data Index: 3210000 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2022. Min Range: -5.2022
Max Act: 4.8897. Min Act: -0.1700
Data Index: 2017452 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2022. Min Range: -5.2022
Max Act: 4.8584. Min Act: -0.1700
Data Index: 4671986 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2022. Min Range: -5.2022
Max Act: 4.8584. Min Act: -0.1700
Data Index: 6916123 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2022. Min Range: -5.2022
Max Act: 4.8272. Min Act: -0.1700
Data Index: 4671993 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2022. Min Range: -5.2022
Max Act: 4.8272. Min Act: -0.1700
Data Index: 5458479 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2022. Min Range: -5.2022
Max Act: 4.8272. Min Act: -0.1700
Data Index: 6805359 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2022. Min Range: -5.2022
Max Act: 4.8272. Min Act: -0.1700
Data Index: 8424894 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2022. Min Range: -5.2022
Max Act: 4.8272. Min Act: -0.1700
Data Index: 5460967 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2022. Min Range: -5.2022
Max Act: 4.7959. Min Act: -0.1700
Data Index: 5460971 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2022. Min Range: -5.2022
Max Act: 4.7959. Min Act: -0.1700
Data Index: 5503085 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #19