Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2021 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5298. Min Range: -5.5298
Max Act: 5.5298. Min Act: -0.1700
Data Index: 2481705 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5298. Min Range: -5.5298
Max Act: 5.4986. Min Act: -0.1700
Data Index: 2304516 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5298. Min Range: -5.5298
Max Act: 5.4361. Min Act: -0.1700
Data Index: 2853488 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5298. Min Range: -5.5298
Max Act: 5.4673. Min Act: -0.1700
Data Index: 8477316 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5298. Min Range: -5.5298
Max Act: 5.4673. Min Act: -0.1700
Data Index: 6196466 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5298. Min Range: -5.5298
Max Act: 5.4361. Min Act: -0.1700
Data Index: 2622767 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5298. Min Range: -5.5298
Max Act: 5.4361. Min Act: -0.1700
Data Index: 3780915 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5298. Min Range: -5.5298
Max Act: 5.4048. Min Act: -0.1700
Data Index: 7302488 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5298. Min Range: -5.5298
Max Act: 5.3736. Min Act: -0.1700
Data Index: 5636820 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5298. Min Range: -5.5298
Max Act: 5.3736. Min Act: -0.1700
Data Index: 8114840 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5298. Min Range: -5.5298
Max Act: 5.3736. Min Act: -0.1700
Data Index: 1669683 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5298. Min Range: -5.5298
Max Act: 5.3736. Min Act: -0.1700
Data Index: 6605159 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5298. Min Range: -5.5298
Max Act: 5.3736. Min Act: -0.1700
Data Index: 1032515 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5298. Min Range: -5.5298
Max Act: 5.3736. Min Act: -0.1700
Data Index: 7823055 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5298. Min Range: -5.5298
Max Act: 5.3111. Min Act: -0.1699
Data Index: 2455348 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5298. Min Range: -5.5298
Max Act: 5.3423. Min Act: -0.1699
Data Index: 3121355 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5298. Min Range: -5.5298
Max Act: 5.3423. Min Act: -0.1700
Data Index: 954997 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5298. Min Range: -5.5298
Max Act: 5.3423. Min Act: -0.1700
Data Index: 7874908 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5298. Min Range: -5.5298
Max Act: 5.3423. Min Act: -0.1700
Data Index: 6051930 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5298. Min Range: -5.5298
Max Act: 5.3423. Min Act: -0.1700
Data Index: 5766475 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #19