Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3046 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 12.9588. Min Range: -12.9588
Max Act: 12.9588. Min Act: -0.1700
Data Index: 8796623 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.9588. Min Range: -12.9588
Max Act: 12.9588. Min Act: -0.1700
Data Index: 689661 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.9588. Min Range: -12.9588
Max Act: 12.8338. Min Act: -0.1700
Data Index: 7928367 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.9588. Min Range: -12.9588
Max Act: 12.8338. Min Act: -0.1700
Data Index: 6807795 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.9588. Min Range: -12.9588
Max Act: 12.7713. Min Act: -0.1700
Data Index: 1081699 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.9588. Min Range: -12.9588
Max Act: 12.7713. Min Act: -0.1700
Data Index: 7398465 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.9588. Min Range: -12.9588
Max Act: 12.6463. Min Act: -0.1700
Data Index: 4232332 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.9588. Min Range: -12.9588
Max Act: 12.5838. Min Act: -0.1700
Data Index: 5666739 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.9588. Min Range: -12.9588
Max Act: 12.5838. Min Act: -0.1700
Data Index: 5426872 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.9588. Min Range: -12.9588
Max Act: 12.5838. Min Act: -0.1700
Data Index: 2828218 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.9588. Min Range: -12.9588
Max Act: 12.5838. Min Act: -0.1700
Data Index: 6196821 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.9588. Min Range: -12.9588
Max Act: 12.5838. Min Act: -0.1700
Data Index: 5693435 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.9588. Min Range: -12.9588
Max Act: 12.5213. Min Act: -0.1700
Data Index: 4207881 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.9588. Min Range: -12.9588
Max Act: 12.5213. Min Act: -0.1700
Data Index: 8728610 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.9588. Min Range: -12.9588
Max Act: 12.5213. Min Act: -0.1700
Data Index: 7082002 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.9588. Min Range: -12.9588
Max Act: 12.5213. Min Act: -0.1700
Data Index: 4430731 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.9588. Min Range: -12.9588
Max Act: 12.4588. Min Act: -0.1700
Data Index: 1645258 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.9588. Min Range: -12.9588
Max Act: 12.4588. Min Act: -0.1700
Data Index: 1397824 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.9588. Min Range: -12.9588
Max Act: 12.4588. Min Act: -0.1700
Data Index: 1078461 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.9588. Min Range: -12.9588
Max Act: 12.3963. Min Act: -0.1700
Data Index: 2627882 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #19