Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 568 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')
Text #0
Max Range: 9.8117. Min Range: -9.8117
Max Act: 9.7492. Min Act: -0.1700
Data Index: 1881817 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.8117. Min Range: -9.8117
Max Act: 9.8117. Min Act: -0.1700
Data Index: 6294106 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.8117. Min Range: -9.8117
Max Act: 9.6242. Min Act: -0.1700
Data Index: 6044701 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.8117. Min Range: -9.8117
Max Act: 9.5617. Min Act: -0.1700
Data Index: 3657971 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.8117. Min Range: -9.8117
Max Act: 9.4992. Min Act: -0.1700
Data Index: 2925427 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.8117. Min Range: -9.8117
Max Act: 9.4992. Min Act: -0.1700
Data Index: 7524435 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.8117. Min Range: -9.8117
Max Act: 9.1867. Min Act: -0.1700
Data Index: 7249683 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.8117. Min Range: -9.8117
Max Act: 9.1867. Min Act: -0.1700
Data Index: 3372434 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.8117. Min Range: -9.8117
Max Act: 9.0617. Min Act: -0.1700
Data Index: 5641163 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.8117. Min Range: -9.8117
Max Act: 9.0617. Min Act: -0.1700
Data Index: 523706 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.8117. Min Range: -9.8117
Max Act: 9.0617. Min Act: -0.1700
Data Index: 1712111 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.8117. Min Range: -9.8117
Max Act: 8.9992. Min Act: -0.1700
Data Index: 3936725 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.8117. Min Range: -9.8117
Max Act: 9.0617. Min Act: -0.1700
Data Index: 5645260 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.8117. Min Range: -9.8117
Max Act: 9.0617. Min Act: -0.1700
Data Index: 7576181 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.8117. Min Range: -9.8117
Max Act: 9.0617. Min Act: -0.1700
Data Index: 6702378 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.8117. Min Range: -9.8117
Max Act: 8.9367. Min Act: -0.1700
Data Index: 7857304 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.8117. Min Range: -9.8117
Max Act: 8.9992. Min Act: -0.1700
Data Index: 2711709 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.8117. Min Range: -9.8117
Max Act: 8.9992. Min Act: -0.1700
Data Index: 5138513 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.8117. Min Range: -9.8117
Max Act: 8.9992. Min Act: -0.1700
Data Index: 2939917 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.8117. Min Range: -9.8117
Max Act: 9.0617. Min Act: -0.1700
Data Index: 1675276 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #19