Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2663 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.3701. Min Range: -8.3701
Max Act: 8.3701. Min Act: -0.1700
Data Index: 2821560 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3701. Min Range: -8.3701
Max Act: 8.0576. Min Act: -0.1700
Data Index: 6617558 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3701. Min Range: -8.3701
Max Act: 7.9326. Min Act: -0.1700
Data Index: 2209144 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3701. Min Range: -8.3701
Max Act: 7.8389. Min Act: -0.1700
Data Index: 5054728 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3701. Min Range: -8.3701
Max Act: 7.7764. Min Act: -0.1700
Data Index: 1331255 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3701. Min Range: -8.3701
Max Act: 7.8389. Min Act: -0.1700
Data Index: 2965387 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3701. Min Range: -8.3701
Max Act: 7.7451. Min Act: -0.1700
Data Index: 7433774 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3701. Min Range: -8.3701
Max Act: 7.7451. Min Act: -0.1700
Data Index: 5458438 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3701. Min Range: -8.3701
Max Act: 7.7764. Min Act: -0.1700
Data Index: 5661612 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3701. Min Range: -8.3701
Max Act: 7.7139. Min Act: -0.1700
Data Index: 6291835 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3701. Min Range: -8.3701
Max Act: 7.5889. Min Act: -0.1700
Data Index: 5393034 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3701. Min Range: -8.3701
Max Act: 7.5264. Min Act: -0.1700
Data Index: 2087487 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3701. Min Range: -8.3701
Max Act: 7.5576. Min Act: -0.1700
Data Index: 7695940 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3701. Min Range: -8.3701
Max Act: 7.5576. Min Act: -0.1700
Data Index: 95322 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3701. Min Range: -8.3701
Max Act: 7.5264. Min Act: -0.1700
Data Index: 6387920 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3701. Min Range: -8.3701
Max Act: 7.5264. Min Act: -0.1700
Data Index: 4653431 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3701. Min Range: -8.3701
Max Act: 7.4951. Min Act: -0.1700
Data Index: 144376 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3701. Min Range: -8.3701
Max Act: 7.4951. Min Act: -0.1700
Data Index: 1401766 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3701. Min Range: -8.3701
Max Act: 7.4951. Min Act: -0.1700
Data Index: 1235795 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3701. Min Range: -8.3701
Max Act: 7.4951. Min Act: -0.1700
Data Index: 2986576 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #19