Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2223 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.8219. Min Range: -6.8219
Max Act: 6.8219. Min Act: -0.1700
Data Index: 2865448 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8219. Min Range: -6.8219
Max Act: 6.7594. Min Act: -0.1700
Data Index: 6416627 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8219. Min Range: -6.8219
Max Act: 6.7594. Min Act: -0.1700
Data Index: 4001269 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8219. Min Range: -6.8219
Max Act: 6.6969. Min Act: -0.1700
Data Index: 5737827 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8219. Min Range: -6.8219
Max Act: 6.6344. Min Act: -0.1700
Data Index: 2492599 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8219. Min Range: -6.8219
Max Act: 6.6344. Min Act: -0.1700
Data Index: 8576109 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8219. Min Range: -6.8219
Max Act: 6.6344. Min Act: -0.1700
Data Index: 481395 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8219. Min Range: -6.8219
Max Act: 6.6344. Min Act: -0.1700
Data Index: 5122723 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8219. Min Range: -6.8219
Max Act: 6.6031. Min Act: -0.1700
Data Index: 2489286 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8219. Min Range: -6.8219
Max Act: 6.6031. Min Act: -0.1700
Data Index: 6603206 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8219. Min Range: -6.8219
Max Act: 6.5719. Min Act: -0.1700
Data Index: 6862033 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8219. Min Range: -6.8219
Max Act: 6.5719. Min Act: -0.1700
Data Index: 7016849 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8219. Min Range: -6.8219
Max Act: 6.5406. Min Act: -0.1700
Data Index: 1454112 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8219. Min Range: -6.8219
Max Act: 6.5406. Min Act: -0.1700
Data Index: 928582 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8219. Min Range: -6.8219
Max Act: 6.5406. Min Act: -0.1700
Data Index: 2820195 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8219. Min Range: -6.8219
Max Act: 6.5094. Min Act: -0.1700
Data Index: 1858693 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8219. Min Range: -6.8219
Max Act: 6.5094. Min Act: -0.1700
Data Index: 2007268 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8219. Min Range: -6.8219
Max Act: 6.5094. Min Act: -0.1700
Data Index: 8265985 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8219. Min Range: -6.8219
Max Act: 6.5094. Min Act: -0.1700
Data Index: 1847385 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8219. Min Range: -6.8219
Max Act: 6.4469. Min Act: -0.1700
Data Index: 7504360 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #19