Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3188 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.0941. Min Range: -5.0941
Max Act: 5.0941. Min Act: -0.1700
Data Index: 8518937 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0941. Min Range: -5.0941
Max Act: 5.0316. Min Act: -0.1700
Data Index: 7267017 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0941. Min Range: -5.0941
Max Act: 5.0316. Min Act: -0.1700
Data Index: 4912697 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0941. Min Range: -5.0941
Max Act: 5.0003. Min Act: -0.1700
Data Index: 1903711 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0941. Min Range: -5.0941
Max Act: 4.9691. Min Act: -0.1700
Data Index: 6365021 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0941. Min Range: -5.0941
Max Act: 4.9691. Min Act: -0.1700
Data Index: 4959721 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0941. Min Range: -5.0941
Max Act: 4.9378. Min Act: -0.1700
Data Index: 3008075 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0941. Min Range: -5.0941
Max Act: 4.9378. Min Act: -0.1700
Data Index: 5687539 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0941. Min Range: -5.0941
Max Act: 4.8753. Min Act: -0.1700
Data Index: 6874355 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0941. Min Range: -5.0941
Max Act: 4.9066. Min Act: -0.1700
Data Index: 8291592 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0941. Min Range: -5.0941
Max Act: 4.8753. Min Act: -0.1700
Data Index: 5850800 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0941. Min Range: -5.0941
Max Act: 4.8753. Min Act: -0.1700
Data Index: 2087734 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0941. Min Range: -5.0941
Max Act: 4.8753. Min Act: -0.1700
Data Index: 4437389 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0941. Min Range: -5.0941
Max Act: 4.8441. Min Act: -0.1700
Data Index: 7319973 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0941. Min Range: -5.0941
Max Act: 4.8128. Min Act: -0.1700
Data Index: 568482 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0941. Min Range: -5.0941
Max Act: 4.8128. Min Act: -0.1700
Data Index: 5684098 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0941. Min Range: -5.0941
Max Act: 4.8128. Min Act: -0.1700
Data Index: 3305895 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0941. Min Range: -5.0941
Max Act: 4.8128. Min Act: -0.1700
Data Index: 4874015 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0941. Min Range: -5.0941
Max Act: 4.8128. Min Act: -0.1700
Data Index: 650498 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0941. Min Range: -5.0941
Max Act: 4.7816. Min Act: -0.1700
Data Index: 5605002 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #19