Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3936 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6835. Min Range: -5.6835
Max Act: 5.6835. Min Act: -0.1700
Data Index: 8822133 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6835. Min Range: -5.6835
Max Act: 5.6210. Min Act: -0.1700
Data Index: 8237698 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6835. Min Range: -5.6835
Max Act: 5.5585. Min Act: -0.1700
Data Index: 751180 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6835. Min Range: -5.6835
Max Act: 5.4648. Min Act: -0.1700
Data Index: 7396128 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6835. Min Range: -5.6835
Max Act: 5.4335. Min Act: -0.1700
Data Index: 6491336 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6835. Min Range: -5.6835
Max Act: 5.4023. Min Act: -0.1700
Data Index: 7010310 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6835. Min Range: -5.6835
Max Act: 5.3398. Min Act: -0.1700
Data Index: 4873724 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6835. Min Range: -5.6835
Max Act: 5.3085. Min Act: -0.1700
Data Index: 2135629 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6835. Min Range: -5.6835
Max Act: 5.2773. Min Act: -0.1700
Data Index: 7152740 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6835. Min Range: -5.6835
Max Act: 5.2773. Min Act: -0.1700
Data Index: 7454669 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6835. Min Range: -5.6835
Max Act: 5.2773. Min Act: -0.1700
Data Index: 6341832 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6835. Min Range: -5.6835
Max Act: 5.2773. Min Act: -0.1700
Data Index: 6142660 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6835. Min Range: -5.6835
Max Act: 5.2460. Min Act: -0.1700
Data Index: 7652541 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6835. Min Range: -5.6835
Max Act: 5.2148. Min Act: -0.1700
Data Index: 4316006 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6835. Min Range: -5.6835
Max Act: 5.1835. Min Act: -0.1700
Data Index: 4015356 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6835. Min Range: -5.6835
Max Act: 5.1835. Min Act: -0.1700
Data Index: 5982647 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6835. Min Range: -5.6835
Max Act: 5.1835. Min Act: -0.1700
Data Index: 6487361 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6835. Min Range: -5.6835
Max Act: 5.1835. Min Act: -0.1700
Data Index: 4937087 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6835. Min Range: -5.6835
Max Act: 5.1835. Min Act: -0.1700
Data Index: 2683728 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6835. Min Range: -5.6835
Max Act: 5.1835. Min Act: -0.1700
Data Index: 6305927 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #19