Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3543 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4016. Min Range: -7.4016
Max Act: 7.4016. Min Act: -0.1700
Data Index: 8356016 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4016. Min Range: -7.4016
Max Act: 7.3703. Min Act: -0.1700
Data Index: 110929 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4016. Min Range: -7.4016
Max Act: 7.0891. Min Act: -0.1700
Data Index: 7495878 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4016. Min Range: -7.4016
Max Act: 7.0266. Min Act: -0.1700
Data Index: 1574617 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4016. Min Range: -7.4016
Max Act: 7.0266. Min Act: -0.1700
Data Index: 7019272 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4016. Min Range: -7.4016
Max Act: 6.9641. Min Act: -0.1700
Data Index: 5280745 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4016. Min Range: -7.4016
Max Act: 6.9328. Min Act: -0.1700
Data Index: 6091802 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4016. Min Range: -7.4016
Max Act: 6.9016. Min Act: -0.1700
Data Index: 574429 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4016. Min Range: -7.4016
Max Act: 6.8391. Min Act: -0.1700
Data Index: 3820566 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4016. Min Range: -7.4016
Max Act: 6.8391. Min Act: -0.1700
Data Index: 3494439 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4016. Min Range: -7.4016
Max Act: 6.8078. Min Act: -0.1700
Data Index: 8795165 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4016. Min Range: -7.4016
Max Act: 6.8391. Min Act: -0.1700
Data Index: 5895699 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4016. Min Range: -7.4016
Max Act: 6.7766. Min Act: -0.1700
Data Index: 5779749 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4016. Min Range: -7.4016
Max Act: 6.7766. Min Act: -0.1700
Data Index: 8811432 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4016. Min Range: -7.4016
Max Act: 6.7453. Min Act: -0.1700
Data Index: 2525629 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4016. Min Range: -7.4016
Max Act: 6.7453. Min Act: -0.1700
Data Index: 2332245 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4016. Min Range: -7.4016
Max Act: 6.7141. Min Act: -0.1700
Data Index: 8342658 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4016. Min Range: -7.4016
Max Act: 6.7141. Min Act: -0.1700
Data Index: 7600325 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4016. Min Range: -7.4016
Max Act: 6.7141. Min Act: -0.1700
Data Index: 560900 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4016. Min Range: -7.4016
Max Act: 6.7141. Min Act: -0.1700
Data Index: 2061569 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #19