Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2700 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.7611. Min Range: -6.7611
Max Act: 6.7611. Min Act: -0.1700
Data Index: 7310299 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7611. Min Range: -6.7611
Max Act: 6.6048. Min Act: -0.1700
Data Index: 4162334 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7611. Min Range: -6.7611
Max Act: 6.4486. Min Act: -0.1700
Data Index: 4424258 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7611. Min Range: -6.7611
Max Act: 6.3861. Min Act: -0.1700
Data Index: 553070 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7611. Min Range: -6.7611
Max Act: 6.3861. Min Act: -0.1700
Data Index: 7768638 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7611. Min Range: -6.7611
Max Act: 6.3861. Min Act: -0.1700
Data Index: 7005023 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7611. Min Range: -6.7611
Max Act: 6.3548. Min Act: -0.1700
Data Index: 826178 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7611. Min Range: -6.7611
Max Act: 6.3236. Min Act: -0.1700
Data Index: 8107714 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7611. Min Range: -6.7611
Max Act: 6.2923. Min Act: -0.1700
Data Index: 5262271 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7611. Min Range: -6.7611
Max Act: 6.2923. Min Act: -0.1700
Data Index: 5488721 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7611. Min Range: -6.7611
Max Act: 6.1673. Min Act: -0.1700
Data Index: 1708976 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7611. Min Range: -6.7611
Max Act: 6.1673. Min Act: -0.1700
Data Index: 3412278 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7611. Min Range: -6.7611
Max Act: 6.1361. Min Act: -0.1700
Data Index: 8822997 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7611. Min Range: -6.7611
Max Act: 6.1048. Min Act: -0.1700
Data Index: 8751116 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7611. Min Range: -6.7611
Max Act: 6.0736. Min Act: -0.1700
Data Index: 7829859 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7611. Min Range: -6.7611
Max Act: 6.1361. Min Act: -0.1700
Data Index: 5632858 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7611. Min Range: -6.7611
Max Act: 6.1048. Min Act: -0.1700
Data Index: 7978071 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7611. Min Range: -6.7611
Max Act: 6.1048. Min Act: -0.1700
Data Index: 8758564 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7611. Min Range: -6.7611
Max Act: 6.0423. Min Act: -0.1700
Data Index: 2697703 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7611. Min Range: -6.7611
Max Act: 6.1048. Min Act: -0.1700
Data Index: 8576200 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #19