Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5798 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1117. Min Range: -6.1117
Max Act: 6.1117. Min Act: -0.1700
Data Index: 4113615 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1117. Min Range: -6.1117
Max Act: 5.9242. Min Act: -0.1700
Data Index: 6295265 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1117. Min Range: -6.1117
Max Act: 5.8305. Min Act: -0.1700
Data Index: 1440928 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1117. Min Range: -6.1117
Max Act: 5.7992. Min Act: -0.1700
Data Index: 5394803 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1117. Min Range: -6.1117
Max Act: 5.7680. Min Act: -0.1700
Data Index: 5325868 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1117. Min Range: -6.1117
Max Act: 5.7680. Min Act: -0.1700
Data Index: 7098973 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1117. Min Range: -6.1117
Max Act: 5.7680. Min Act: -0.1700
Data Index: 6728957 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1117. Min Range: -6.1117
Max Act: 5.7367. Min Act: -0.1700
Data Index: 2159635 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1117. Min Range: -6.1117
Max Act: 5.7055. Min Act: -0.1700
Data Index: 459236 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1117. Min Range: -6.1117
Max Act: 5.7055. Min Act: -0.1700
Data Index: 4791735 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1117. Min Range: -6.1117
Max Act: 5.6117. Min Act: -0.1700
Data Index: 4225390 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1117. Min Range: -6.1117
Max Act: 5.6117. Min Act: -0.1700
Data Index: 2793923 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1117. Min Range: -6.1117
Max Act: 5.6117. Min Act: -0.1700
Data Index: 738552 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1117. Min Range: -6.1117
Max Act: 5.5805. Min Act: -0.1700
Data Index: 5594744 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1117. Min Range: -6.1117
Max Act: 5.5492. Min Act: -0.1700
Data Index: 817079 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1117. Min Range: -6.1117
Max Act: 5.5492. Min Act: -0.1700
Data Index: 2133228 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1117. Min Range: -6.1117
Max Act: 5.5492. Min Act: -0.1700
Data Index: 4859522 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1117. Min Range: -6.1117
Max Act: 5.5180. Min Act: -0.1700
Data Index: 5724633 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1117. Min Range: -6.1117
Max Act: 5.5180. Min Act: -0.1700
Data Index: 5886730 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1117. Min Range: -6.1117
Max Act: 5.4867. Min Act: -0.1700
Data Index: 4665369 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #19