Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4086 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.0816. Min Range: -6.0816
Max Act: 6.0816. Min Act: -0.1700
Data Index: 8100196 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0816. Min Range: -6.0816
Max Act: 6.0816. Min Act: -0.1700
Data Index: 8102400 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0816. Min Range: -6.0816
Max Act: 5.8941. Min Act: -0.1700
Data Index: 821975 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0816. Min Range: -6.0816
Max Act: 5.9566. Min Act: -0.1700
Data Index: 8245944 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0816. Min Range: -6.0816
Max Act: 5.8316. Min Act: -0.1700
Data Index: 8383013 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0816. Min Range: -6.0816
Max Act: 5.8004. Min Act: -0.1700
Data Index: 4666109 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0816. Min Range: -6.0816
Max Act: 5.8004. Min Act: -0.1700
Data Index: 365089 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0816. Min Range: -6.0816
Max Act: 5.8316. Min Act: -0.1700
Data Index: 1057713 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0816. Min Range: -6.0816
Max Act: 5.8004. Min Act: -0.1700
Data Index: 6561464 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0816. Min Range: -6.0816
Max Act: 5.7379. Min Act: -0.1700
Data Index: 5944927 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0816. Min Range: -6.0816
Max Act: 5.7066. Min Act: -0.1700
Data Index: 4584488 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0816. Min Range: -6.0816
Max Act: 5.7066. Min Act: -0.1700
Data Index: 1084004 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0816. Min Range: -6.0816
Max Act: 5.7066. Min Act: -0.1700
Data Index: 998413 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0816. Min Range: -6.0816
Max Act: 5.6754. Min Act: -0.1700
Data Index: 5492179 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0816. Min Range: -6.0816
Max Act: 5.6129. Min Act: -0.1700
Data Index: 126698 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0816. Min Range: -6.0816
Max Act: 5.6441. Min Act: -0.1700
Data Index: 1057716 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0816. Min Range: -6.0816
Max Act: 5.6129. Min Act: -0.1700
Data Index: 6769565 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0816. Min Range: -6.0816
Max Act: 5.6129. Min Act: -0.1700
Data Index: 4532595 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0816. Min Range: -6.0816
Max Act: 5.6441. Min Act: -0.1700
Data Index: 6820158 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0816. Min Range: -6.0816
Max Act: 5.6129. Min Act: -0.1700
Data Index: 3744754 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #19