Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1079 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1842. Min Range: -7.1842
Max Act: 7.1842. Min Act: -0.1700
Data Index: 4842498 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1842. Min Range: -7.1842
Max Act: 7.0592. Min Act: -0.1700
Data Index: 6114721 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1842. Min Range: -7.1842
Max Act: 6.9342. Min Act: -0.1700
Data Index: 5815205 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1842. Min Range: -7.1842
Max Act: 6.8092. Min Act: -0.1700
Data Index: 3659643 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1842. Min Range: -7.1842
Max Act: 6.7467. Min Act: -0.1700
Data Index: 5220541 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1842. Min Range: -7.1842
Max Act: 6.6529. Min Act: -0.1700
Data Index: 7041243 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1842. Min Range: -7.1842
Max Act: 6.5904. Min Act: -0.1700
Data Index: 5220542 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1842. Min Range: -7.1842
Max Act: 6.6217. Min Act: -0.1700
Data Index: 4180758 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1842. Min Range: -7.1842
Max Act: 6.4342. Min Act: -0.1700
Data Index: 4007789 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1842. Min Range: -7.1842
Max Act: 6.4342. Min Act: -0.1700
Data Index: 1414690 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1842. Min Range: -7.1842
Max Act: 6.3717. Min Act: -0.1700
Data Index: 3980905 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1842. Min Range: -7.1842
Max Act: 6.3717. Min Act: -0.1700
Data Index: 7038113 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1842. Min Range: -7.1842
Max Act: 6.3404. Min Act: -0.1700
Data Index: 8813132 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1842. Min Range: -7.1842
Max Act: 6.2779. Min Act: -0.1700
Data Index: 6939650 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1842. Min Range: -7.1842
Max Act: 6.2467. Min Act: -0.1700
Data Index: 1873666 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1842. Min Range: -7.1842
Max Act: 6.2154. Min Act: -0.1700
Data Index: 3366039 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1842. Min Range: -7.1842
Max Act: 6.2154. Min Act: -0.1700
Data Index: 1750814 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1842. Min Range: -7.1842
Max Act: 6.1842. Min Act: -0.1700
Data Index: 3928870 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1842. Min Range: -7.1842
Max Act: 6.1842. Min Act: -0.1700
Data Index: 4695658 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1842. Min Range: -7.1842
Max Act: 6.1529. Min Act: -0.1700
Data Index: 1864289 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #19