Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2476 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.8995. Min Range: -7.8995
Max Act: 7.8995. Min Act: -0.1700
Data Index: 5584100 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8995. Min Range: -7.8995
Max Act: 7.8370. Min Act: -0.1700
Data Index: 5439516 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8995. Min Range: -7.8995
Max Act: 7.8057. Min Act: -0.1700
Data Index: 5167065 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8995. Min Range: -7.8995
Max Act: 7.7745. Min Act: -0.1700
Data Index: 135397 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8995. Min Range: -7.8995
Max Act: 7.7432. Min Act: -0.1700
Data Index: 1945268 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8995. Min Range: -7.8995
Max Act: 7.7432. Min Act: -0.1700
Data Index: 1862882 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8995. Min Range: -7.8995
Max Act: 7.6807. Min Act: -0.1700
Data Index: 8461794 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8995. Min Range: -7.8995
Max Act: 7.6807. Min Act: -0.1700
Data Index: 4574470 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8995. Min Range: -7.8995
Max Act: 7.6495. Min Act: -0.1700
Data Index: 2346826 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8995. Min Range: -7.8995
Max Act: 7.6495. Min Act: -0.1700
Data Index: 4952634 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8995. Min Range: -7.8995
Max Act: 7.6495. Min Act: -0.1700
Data Index: 6939017 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8995. Min Range: -7.8995
Max Act: 7.6182. Min Act: -0.1700
Data Index: 2560838 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8995. Min Range: -7.8995
Max Act: 7.5870. Min Act: -0.1700
Data Index: 3876006 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8995. Min Range: -7.8995
Max Act: 7.5557. Min Act: -0.1700
Data Index: 7049135 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8995. Min Range: -7.8995
Max Act: 7.5245. Min Act: -0.1700
Data Index: 789514 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8995. Min Range: -7.8995
Max Act: 7.5557. Min Act: -0.1700
Data Index: 7856072 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8995. Min Range: -7.8995
Max Act: 7.4307. Min Act: -0.1700
Data Index: 452659 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8995. Min Range: -7.8995
Max Act: 7.4307. Min Act: -0.1700
Data Index: 7611970 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8995. Min Range: -7.8995
Max Act: 7.4620. Min Act: -0.1700
Data Index: 7383859 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8995. Min Range: -7.8995
Max Act: 7.3995. Min Act: -0.1700
Data Index: 2330830 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #19