Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3724 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8589. Min Range: -8.8589
Max Act: 8.8589. Min Act: -0.1700
Data Index: 7688721 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8589. Min Range: -8.8589
Max Act: 8.5464. Min Act: -0.1700
Data Index: 540879 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8589. Min Range: -8.8589
Max Act: 8.4214. Min Act: -0.1700
Data Index: 1379606 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8589. Min Range: -8.8589
Max Act: 8.4839. Min Act: -0.1700
Data Index: 6569229 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8589. Min Range: -8.8589
Max Act: 8.4214. Min Act: -0.1700
Data Index: 3031222 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8589. Min Range: -8.8589
Max Act: 8.3589. Min Act: -0.1700
Data Index: 281284 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8589. Min Range: -8.8589
Max Act: 8.3589. Min Act: -0.1700
Data Index: 7930994 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8589. Min Range: -8.8589
Max Act: 8.3589. Min Act: -0.1700
Data Index: 3002460 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8589. Min Range: -8.8589
Max Act: 8.2964. Min Act: -0.1700
Data Index: 4536729 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8589. Min Range: -8.8589
Max Act: 8.2964. Min Act: -0.1700
Data Index: 3007261 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8589. Min Range: -8.8589
Max Act: 8.2964. Min Act: -0.1700
Data Index: 5038922 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8589. Min Range: -8.8589
Max Act: 8.2339. Min Act: -0.1700
Data Index: 7136875 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8589. Min Range: -8.8589
Max Act: 8.2339. Min Act: -0.1700
Data Index: 6626525 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8589. Min Range: -8.8589
Max Act: 8.2339. Min Act: -0.1700
Data Index: 6247200 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8589. Min Range: -8.8589
Max Act: 8.1714. Min Act: -0.1700
Data Index: 5627890 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8589. Min Range: -8.8589
Max Act: 8.1714. Min Act: -0.1700
Data Index: 1535317 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8589. Min Range: -8.8589
Max Act: 8.1714. Min Act: -0.1700
Data Index: 4349388 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8589. Min Range: -8.8589
Max Act: 8.2339. Min Act: -0.1700
Data Index: 4046057 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8589. Min Range: -8.8589
Max Act: 8.1714. Min Act: -0.1700
Data Index: 1578881 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8589. Min Range: -8.8589
Max Act: 8.1089. Min Act: -0.1700
Data Index: 6884110 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #19