Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2598 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.2821. Min Range: -6.2821
Max Act: 6.2821. Min Act: -0.1700
Data Index: 7900926 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2821. Min Range: -6.2821
Max Act: 6.2821. Min Act: -0.1700
Data Index: 7821363 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2821. Min Range: -6.2821
Max Act: 6.2508. Min Act: -0.1700
Data Index: 841304 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2821. Min Range: -6.2821
Max Act: 6.1258. Min Act: -0.1700
Data Index: 1501364 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2821. Min Range: -6.2821
Max Act: 6.1571. Min Act: -0.1700
Data Index: 7768441 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2821. Min Range: -6.2821
Max Act: 6.1258. Min Act: -0.1700
Data Index: 2860195 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2821. Min Range: -6.2821
Max Act: 6.0946. Min Act: -0.1700
Data Index: 611869 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2821. Min Range: -6.2821
Max Act: 6.0321. Min Act: -0.1700
Data Index: 8007307 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2821. Min Range: -6.2821
Max Act: 5.9696. Min Act: -0.1700
Data Index: 6074441 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2821. Min Range: -6.2821
Max Act: 6.0008. Min Act: -0.1700
Data Index: 7841159 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2821. Min Range: -6.2821
Max Act: 5.9071. Min Act: -0.1700
Data Index: 5688640 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2821. Min Range: -6.2821
Max Act: 5.9071. Min Act: -0.1700
Data Index: 5760638 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2821. Min Range: -6.2821
Max Act: 5.8758. Min Act: -0.1700
Data Index: 3828105 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2821. Min Range: -6.2821
Max Act: 5.8758. Min Act: -0.1700
Data Index: 8046638 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2821. Min Range: -6.2821
Max Act: 5.8446. Min Act: -0.1700
Data Index: 4347218 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2821. Min Range: -6.2821
Max Act: 5.8133. Min Act: -0.1700
Data Index: 2234641 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2821. Min Range: -6.2821
Max Act: 5.8446. Min Act: -0.1700
Data Index: 1861859 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2821. Min Range: -6.2821
Max Act: 5.8133. Min Act: -0.1700
Data Index: 1884974 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2821. Min Range: -6.2821
Max Act: 5.8446. Min Act: -0.1700
Data Index: 2893717 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2821. Min Range: -6.2821
Max Act: 5.7821. Min Act: -0.1700
Data Index: 5760639 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #19