Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4682 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.4593. Min Range: -6.4593
Max Act: 6.4593. Min Act: -0.1700
Data Index: 5228248 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4593. Min Range: -6.4593
Max Act: 6.1155. Min Act: -0.1700
Data Index: 7572862 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4593. Min Range: -6.4593
Max Act: 5.9905. Min Act: -0.1700
Data Index: 2152799 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4593. Min Range: -6.4593
Max Act: 5.9593. Min Act: -0.1700
Data Index: 3459341 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4593. Min Range: -6.4593
Max Act: 5.9593. Min Act: -0.1700
Data Index: 2629961 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4593. Min Range: -6.4593
Max Act: 5.8655. Min Act: -0.1700
Data Index: 768002 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4593. Min Range: -6.4593
Max Act: 5.8968. Min Act: -0.1700
Data Index: 7638631 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4593. Min Range: -6.4593
Max Act: 5.9280. Min Act: -0.1700
Data Index: 6560623 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4593. Min Range: -6.4593
Max Act: 5.8968. Min Act: -0.1700
Data Index: 8680840 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4593. Min Range: -6.4593
Max Act: 5.8655. Min Act: -0.1700
Data Index: 2732906 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4593. Min Range: -6.4593
Max Act: 5.8968. Min Act: -0.1700
Data Index: 4954248 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4593. Min Range: -6.4593
Max Act: 5.8343. Min Act: -0.1700
Data Index: 1332458 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4593. Min Range: -6.4593
Max Act: 5.8343. Min Act: -0.1700
Data Index: 7248810 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4593. Min Range: -6.4593
Max Act: 5.8343. Min Act: -0.1700
Data Index: 7027031 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4593. Min Range: -6.4593
Max Act: 5.8030. Min Act: -0.1700
Data Index: 8417091 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4593. Min Range: -6.4593
Max Act: 5.8343. Min Act: -0.1700
Data Index: 5422567 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4593. Min Range: -6.4593
Max Act: 5.8030. Min Act: -0.1700
Data Index: 3911722 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4593. Min Range: -6.4593
Max Act: 5.7718. Min Act: -0.1700
Data Index: 7014815 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4593. Min Range: -6.4593
Max Act: 5.7718. Min Act: -0.1700
Data Index: 428218 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4593. Min Range: -6.4593
Max Act: 5.8030. Min Act: -0.1700
Data Index: 198727 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #19