Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2913 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.9622. Min Range: -5.9622
Max Act: 5.9622. Min Act: -0.1700
Data Index: 5341543 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9622. Min Range: -5.9622
Max Act: 5.6810. Min Act: -0.1700
Data Index: 1059097 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9622. Min Range: -5.9622
Max Act: 5.5560. Min Act: -0.1700
Data Index: 7215243 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9622. Min Range: -5.9622
Max Act: 5.5560. Min Act: -0.1700
Data Index: 3787435 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9622. Min Range: -5.9622
Max Act: 5.4935. Min Act: -0.1700
Data Index: 7549949 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9622. Min Range: -5.9622
Max Act: 5.4935. Min Act: -0.1700
Data Index: 2902084 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9622. Min Range: -5.9622
Max Act: 5.4935. Min Act: -0.1700
Data Index: 1059099 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9622. Min Range: -5.9622
Max Act: 5.4622. Min Act: -0.1700
Data Index: 5681913 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9622. Min Range: -5.9622
Max Act: 5.4310. Min Act: -0.1700
Data Index: 4186697 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9622. Min Range: -5.9622
Max Act: 5.4310. Min Act: -0.1700
Data Index: 8072955 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9622. Min Range: -5.9622
Max Act: 5.4310. Min Act: -0.1700
Data Index: 7309400 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9622. Min Range: -5.9622
Max Act: 5.3685. Min Act: -0.1700
Data Index: 2150506 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9622. Min Range: -5.9622
Max Act: 5.3997. Min Act: -0.1700
Data Index: 1721778 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9622. Min Range: -5.9622
Max Act: 5.3685. Min Act: -0.1700
Data Index: 1831509 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9622. Min Range: -5.9622
Max Act: 5.3372. Min Act: -0.1700
Data Index: 590768 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9622. Min Range: -5.9622
Max Act: 5.3372. Min Act: -0.1700
Data Index: 4416888 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9622. Min Range: -5.9622
Max Act: 5.3685. Min Act: -0.1700
Data Index: 6500586 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9622. Min Range: -5.9622
Max Act: 5.3372. Min Act: -0.1700
Data Index: 1361823 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9622. Min Range: -5.9622
Max Act: 5.3372. Min Act: -0.1700
Data Index: 2818925 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9622. Min Range: -5.9622
Max Act: 5.3372. Min Act: -0.1700
Data Index: 570263 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #19