Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1890 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8014. Min Range: -6.8014
Max Act: 6.8014. Min Act: -0.1700
Data Index: 4896574 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8014. Min Range: -6.8014
Max Act: 6.8014. Min Act: -0.1700
Data Index: 6677312 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8014. Min Range: -6.8014
Max Act: 6.7076. Min Act: -0.1700
Data Index: 55192 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8014. Min Range: -6.8014
Max Act: 6.4889. Min Act: -0.1700
Data Index: 4633275 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8014. Min Range: -6.8014
Max Act: 6.4264. Min Act: -0.1700
Data Index: 396495 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8014. Min Range: -6.8014
Max Act: 6.3951. Min Act: -0.1700
Data Index: 2114494 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8014. Min Range: -6.8014
Max Act: 6.3639. Min Act: -0.1700
Data Index: 7857786 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8014. Min Range: -6.8014
Max Act: 6.3326. Min Act: -0.1700
Data Index: 1367485 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8014. Min Range: -6.8014
Max Act: 6.3014. Min Act: -0.1700
Data Index: 5044926 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8014. Min Range: -6.8014
Max Act: 6.2076. Min Act: -0.1700
Data Index: 8360836 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8014. Min Range: -6.8014
Max Act: 6.2701. Min Act: -0.1700
Data Index: 2061488 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8014. Min Range: -6.8014
Max Act: 6.2389. Min Act: -0.1700
Data Index: 5667436 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8014. Min Range: -6.8014
Max Act: 6.2076. Min Act: -0.1700
Data Index: 2577021 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8014. Min Range: -6.8014
Max Act: 6.2076. Min Act: -0.1700
Data Index: 8318741 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8014. Min Range: -6.8014
Max Act: 6.2076. Min Act: -0.1700
Data Index: 6969923 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8014. Min Range: -6.8014
Max Act: 6.1764. Min Act: -0.1700
Data Index: 8042015 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8014. Min Range: -6.8014
Max Act: 6.1451. Min Act: -0.1700
Data Index: 851265 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8014. Min Range: -6.8014
Max Act: 6.1139. Min Act: -0.1700
Data Index: 4123490 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8014. Min Range: -6.8014
Max Act: 6.1139. Min Act: -0.1700
Data Index: 5920225 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8014. Min Range: -6.8014
Max Act: 6.1139. Min Act: -0.1700
Data Index: 6509794 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #19