Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3494 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.3625. Min Range: -6.3625
Max Act: 6.3625. Min Act: -0.1700
Data Index: 3536170 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3625. Min Range: -6.3625
Max Act: 6.1125. Min Act: -0.1700
Data Index: 1052169 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3625. Min Range: -6.3625
Max Act: 6.0813. Min Act: -0.1700
Data Index: 31627 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3625. Min Range: -6.3625
Max Act: 6.0500. Min Act: -0.1700
Data Index: 6896248 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3625. Min Range: -6.3625
Max Act: 6.0813. Min Act: -0.1700
Data Index: 4599815 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3625. Min Range: -6.3625
Max Act: 6.0500. Min Act: -0.1700
Data Index: 3128559 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3625. Min Range: -6.3625
Max Act: 6.0188. Min Act: -0.1700
Data Index: 5258119 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3625. Min Range: -6.3625
Max Act: 6.0188. Min Act: -0.1700
Data Index: 5494886 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3625. Min Range: -6.3625
Max Act: 5.9875. Min Act: -0.1700
Data Index: 422098 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3625. Min Range: -6.3625
Max Act: 5.9563. Min Act: -0.1700
Data Index: 1692477 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3625. Min Range: -6.3625
Max Act: 5.9875. Min Act: -0.1700
Data Index: 2626547 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3625. Min Range: -6.3625
Max Act: 5.9563. Min Act: -0.1700
Data Index: 1592988 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3625. Min Range: -6.3625
Max Act: 5.9563. Min Act: -0.1700
Data Index: 6233319 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3625. Min Range: -6.3625
Max Act: 5.9563. Min Act: -0.1700
Data Index: 5682114 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3625. Min Range: -6.3625
Max Act: 5.9250. Min Act: -0.1700
Data Index: 4965167 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3625. Min Range: -6.3625
Max Act: 5.9250. Min Act: -0.1700
Data Index: 1513777 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3625. Min Range: -6.3625
Max Act: 5.9250. Min Act: -0.1700
Data Index: 3880360 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3625. Min Range: -6.3625
Max Act: 5.9250. Min Act: -0.1700
Data Index: 7987799 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3625. Min Range: -6.3625
Max Act: 5.8625. Min Act: -0.1700
Data Index: 7104891 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3625. Min Range: -6.3625
Max Act: 5.8938. Min Act: -0.1700
Data Index: 6675702 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #19