Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1218 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 9.2827. Min Range: -9.2827
Max Act: 9.2827. Min Act: -0.1700
Data Index: 7492878 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.2827. Min Range: -9.2827
Max Act: 9.2202. Min Act: -0.1700
Data Index: 523012 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.2827. Min Range: -9.2827
Max Act: 9.0952. Min Act: -0.1700
Data Index: 7947773 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.2827. Min Range: -9.2827
Max Act: 9.1577. Min Act: -0.1700
Data Index: 8407398 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.2827. Min Range: -9.2827
Max Act: 9.0952. Min Act: -0.1700
Data Index: 7242309 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.2827. Min Range: -9.2827
Max Act: 8.9702. Min Act: -0.1700
Data Index: 6354553 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.2827. Min Range: -9.2827
Max Act: 8.9702. Min Act: -0.1700
Data Index: 3942619 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.2827. Min Range: -9.2827
Max Act: 8.5952. Min Act: -0.1700
Data Index: 7716713 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.2827. Min Range: -9.2827
Max Act: 8.5952. Min Act: -0.1700
Data Index: 2774452 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.2827. Min Range: -9.2827
Max Act: 8.5952. Min Act: -0.1700
Data Index: 6739322 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.2827. Min Range: -9.2827
Max Act: 8.5327. Min Act: -0.1700
Data Index: 5645459 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.2827. Min Range: -9.2827
Max Act: 8.5327. Min Act: -0.1700
Data Index: 6538424 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.2827. Min Range: -9.2827
Max Act: 8.5327. Min Act: -0.1700
Data Index: 3807930 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.2827. Min Range: -9.2827
Max Act: 8.5327. Min Act: -0.1700
Data Index: 6352582 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.2827. Min Range: -9.2827
Max Act: 8.4702. Min Act: -0.1700
Data Index: 5005907 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.2827. Min Range: -9.2827
Max Act: 8.4077. Min Act: -0.1700
Data Index: 7152406 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.2827. Min Range: -9.2827
Max Act: 8.4077. Min Act: -0.1700
Data Index: 6593987 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.2827. Min Range: -9.2827
Max Act: 8.3452. Min Act: -0.1700
Data Index: 1022621 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.2827. Min Range: -9.2827
Max Act: 8.2827. Min Act: -0.1700
Data Index: 684605 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.2827. Min Range: -9.2827
Max Act: 8.3452. Min Act: -0.1700
Data Index: 8608256 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #19