Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2883 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0320. Min Range: -9.0320
Max Act: 9.0320. Min Act: -0.1700
Data Index: 7116976 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0320. Min Range: -9.0320
Max Act: 8.0320. Min Act: -0.1700
Data Index: 5302275 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0320. Min Range: -9.0320
Max Act: 8.0320. Min Act: -0.1700
Data Index: 1199145 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0320. Min Range: -9.0320
Max Act: 7.9382. Min Act: -0.1700
Data Index: 7806639 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0320. Min Range: -9.0320
Max Act: 7.9382. Min Act: -0.1700
Data Index: 1636949 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0320. Min Range: -9.0320
Max Act: 7.9382. Min Act: -0.1700
Data Index: 6158541 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0320. Min Range: -9.0320
Max Act: 7.8757. Min Act: -0.1700
Data Index: 6325231 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0320. Min Range: -9.0320
Max Act: 7.8445. Min Act: -0.1700
Data Index: 3605786 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0320. Min Range: -9.0320
Max Act: 7.8445. Min Act: -0.1700
Data Index: 721533 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0320. Min Range: -9.0320
Max Act: 7.7507. Min Act: -0.1700
Data Index: 3538095 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0320. Min Range: -9.0320
Max Act: 7.8132. Min Act: -0.1700
Data Index: 8772657 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0320. Min Range: -9.0320
Max Act: 7.7507. Min Act: -0.1700
Data Index: 933363 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0320. Min Range: -9.0320
Max Act: 7.7820. Min Act: -0.1700
Data Index: 6158540 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0320. Min Range: -9.0320
Max Act: 7.7195. Min Act: -0.1700
Data Index: 1520965 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0320. Min Range: -9.0320
Max Act: 7.7195. Min Act: -0.1700
Data Index: 4507843 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0320. Min Range: -9.0320
Max Act: 7.7195. Min Act: -0.1700
Data Index: 1022292 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0320. Min Range: -9.0320
Max Act: 7.6257. Min Act: -0.1700
Data Index: 28229 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0320. Min Range: -9.0320
Max Act: 7.5632. Min Act: -0.1700
Data Index: 1959789 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0320. Min Range: -9.0320
Max Act: 7.5007. Min Act: -0.1700
Data Index: 8265582 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0320. Min Range: -9.0320
Max Act: 7.4695. Min Act: -0.1700
Data Index: 4218113 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #19