Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4146 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.6453. Min Range: -2.6453
Max Act: 2.6453. Min Act: -0.1700
Data Index: 5829009 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6453. Min Range: -2.6453
Max Act: 2.6292. Min Act: -0.1700
Data Index: 117240 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6453. Min Range: -2.6453
Max Act: 2.6292. Min Act: -0.1700
Data Index: 8707960 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6453. Min Range: -2.6453
Max Act: 2.6132. Min Act: -0.1700
Data Index: 312886 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6453. Min Range: -2.6453
Max Act: 2.6132. Min Act: -0.1700
Data Index: 6548173 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6453. Min Range: -2.6453
Max Act: 2.6292. Min Act: -0.1700
Data Index: 7647467 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6453. Min Range: -2.6453
Max Act: 2.5971. Min Act: -0.1700
Data Index: 3936471 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6453. Min Range: -2.6453
Max Act: 2.5971. Min Act: -0.1700
Data Index: 4680868 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6453. Min Range: -2.6453
Max Act: 2.5971. Min Act: -0.1700
Data Index: 4143762 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6453. Min Range: -2.6453
Max Act: 2.5971. Min Act: -0.1700
Data Index: 1112676 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6453. Min Range: -2.6453
Max Act: 2.5971. Min Act: -0.1700
Data Index: 2495919 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6453. Min Range: -2.6453
Max Act: 2.5971. Min Act: -0.1700
Data Index: 3372261 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6453. Min Range: -2.6453
Max Act: 2.5971. Min Act: -0.1700
Data Index: 5530918 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6453. Min Range: -2.6453
Max Act: 2.5810. Min Act: -0.1700
Data Index: 2792112 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6453. Min Range: -2.6453
Max Act: 2.5810. Min Act: -0.1700
Data Index: 7647466 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6453. Min Range: -2.6453
Max Act: 2.5810. Min Act: -0.1700
Data Index: 117241 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6453. Min Range: -2.6453
Max Act: 2.5971. Min Act: -0.1700
Data Index: 5850670 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6453. Min Range: -2.6453
Max Act: 2.5648. Min Act: -0.1700
Data Index: 3031218 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6453. Min Range: -2.6453
Max Act: 2.5648. Min Act: -0.1700
Data Index: 268824 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6453. Min Range: -2.6453
Max Act: 2.5648. Min Act: -0.1700
Data Index: 6936241 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #19