Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 5100 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.8233. Min Range: -6.8233
Max Act: 6.8233. Min Act: -0.1700
Data Index: 8735604 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8233. Min Range: -6.8233
Max Act: 6.6983. Min Act: -0.1700
Data Index: 6102313 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8233. Min Range: -6.8233
Max Act: 6.5733. Min Act: -0.1700
Data Index: 5680474 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8233. Min Range: -6.8233
Max Act: 6.5108. Min Act: -0.1700
Data Index: 6956217 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8233. Min Range: -6.8233
Max Act: 6.4170. Min Act: -0.1700
Data Index: 3182599 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8233. Min Range: -6.8233
Max Act: 6.4483. Min Act: -0.1700
Data Index: 6380585 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8233. Min Range: -6.8233
Max Act: 6.3858. Min Act: -0.1700
Data Index: 8561079 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8233. Min Range: -6.8233
Max Act: 6.3858. Min Act: -0.1700
Data Index: 776825 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8233. Min Range: -6.8233
Max Act: 6.3545. Min Act: -0.1700
Data Index: 7484777 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8233. Min Range: -6.8233
Max Act: 6.3858. Min Act: -0.1700
Data Index: 4174608 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8233. Min Range: -6.8233
Max Act: 6.4170. Min Act: -0.1700
Data Index: 7672221 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8233. Min Range: -6.8233
Max Act: 6.3545. Min Act: -0.1700
Data Index: 3899935 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8233. Min Range: -6.8233
Max Act: 6.3545. Min Act: -0.1700
Data Index: 4084487 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8233. Min Range: -6.8233
Max Act: 6.3233. Min Act: -0.1700
Data Index: 797008 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8233. Min Range: -6.8233
Max Act: 6.3233. Min Act: -0.1700
Data Index: 3206915 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8233. Min Range: -6.8233
Max Act: 6.2920. Min Act: -0.1700
Data Index: 1597441 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8233. Min Range: -6.8233
Max Act: 6.2608. Min Act: -0.1700
Data Index: 5371585 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8233. Min Range: -6.8233
Max Act: 6.2608. Min Act: -0.1700
Data Index: 254434 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8233. Min Range: -6.8233
Max Act: 6.2608. Min Act: -0.1700
Data Index: 5377749 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8233. Min Range: -6.8233
Max Act: 6.2608. Min Act: -0.1700
Data Index: 791729 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #19