Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1745 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2431. Min Range: -6.2431
Max Act: 6.2431. Min Act: -0.1700
Data Index: 1773390 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2431. Min Range: -6.2431
Max Act: 5.9619. Min Act: -0.1700
Data Index: 6997171 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2431. Min Range: -6.2431
Max Act: 5.8681. Min Act: -0.1700
Data Index: 5533875 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2431. Min Range: -6.2431
Max Act: 5.7744. Min Act: -0.1700
Data Index: 232536 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2431. Min Range: -6.2431
Max Act: 5.7431. Min Act: -0.1700
Data Index: 2012225 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2431. Min Range: -6.2431
Max Act: 5.7431. Min Act: -0.1700
Data Index: 4065159 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2431. Min Range: -6.2431
Max Act: 5.6494. Min Act: -0.1700
Data Index: 1773386 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2431. Min Range: -6.2431
Max Act: 5.6181. Min Act: -0.1700
Data Index: 4072817 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2431. Min Range: -6.2431
Max Act: 5.5556. Min Act: -0.1700
Data Index: 899150 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2431. Min Range: -6.2431
Max Act: 5.5869. Min Act: -0.1700
Data Index: 302906 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2431. Min Range: -6.2431
Max Act: 5.5244. Min Act: -0.1700
Data Index: 3699553 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2431. Min Range: -6.2431
Max Act: 5.5556. Min Act: -0.1700
Data Index: 3541196 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2431. Min Range: -6.2431
Max Act: 5.5556. Min Act: -0.1700
Data Index: 6977155 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2431. Min Range: -6.2431
Max Act: 5.5556. Min Act: -0.1700
Data Index: 1853918 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2431. Min Range: -6.2431
Max Act: 5.5556. Min Act: -0.1700
Data Index: 3626830 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2431. Min Range: -6.2431
Max Act: 5.5244. Min Act: -0.1700
Data Index: 5271349 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2431. Min Range: -6.2431
Max Act: 5.5244. Min Act: -0.1700
Data Index: 8707258 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2431. Min Range: -6.2431
Max Act: 5.5244. Min Act: -0.1700
Data Index: 2781585 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2431. Min Range: -6.2431
Max Act: 5.5244. Min Act: -0.1700
Data Index: 8355741 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2431. Min Range: -6.2431
Max Act: 5.4931. Min Act: -0.1700
Data Index: 167635 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #19