Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3741 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7343. Min Range: -6.7343
Max Act: 6.7343. Min Act: -0.1700
Data Index: 1297664 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7343. Min Range: -6.7343
Max Act: 6.5468. Min Act: -0.1700
Data Index: 3363726 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7343. Min Range: -6.7343
Max Act: 6.4531. Min Act: -0.1700
Data Index: 3675895 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7343. Min Range: -6.7343
Max Act: 6.3906. Min Act: -0.1700
Data Index: 6152205 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7343. Min Range: -6.7343
Max Act: 6.3906. Min Act: -0.1700
Data Index: 6979932 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7343. Min Range: -6.7343
Max Act: 6.3593. Min Act: -0.1700
Data Index: 3986360 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7343. Min Range: -6.7343
Max Act: 6.2343. Min Act: -0.1700
Data Index: 7011114 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7343. Min Range: -6.7343
Max Act: 6.2031. Min Act: -0.1700
Data Index: 4658696 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7343. Min Range: -6.7343
Max Act: 6.1406. Min Act: -0.1700
Data Index: 901177 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7343. Min Range: -6.7343
Max Act: 6.1406. Min Act: -0.1700
Data Index: 5083582 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7343. Min Range: -6.7343
Max Act: 6.1406. Min Act: -0.1700
Data Index: 5963161 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7343. Min Range: -6.7343
Max Act: 6.0781. Min Act: -0.1700
Data Index: 1360360 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7343. Min Range: -6.7343
Max Act: 6.0781. Min Act: -0.1700
Data Index: 6901692 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7343. Min Range: -6.7343
Max Act: 6.0781. Min Act: -0.1700
Data Index: 6061172 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7343. Min Range: -6.7343
Max Act: 6.0781. Min Act: -0.1700
Data Index: 3031606 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7343. Min Range: -6.7343
Max Act: 6.0156. Min Act: -0.1700
Data Index: 806914 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7343. Min Range: -6.7343
Max Act: 6.0468. Min Act: -0.1700
Data Index: 1060783 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7343. Min Range: -6.7343
Max Act: 6.0156. Min Act: -0.1700
Data Index: 5179015 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7343. Min Range: -6.7343
Max Act: 5.9843. Min Act: -0.1700
Data Index: 430547 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7343. Min Range: -6.7343
Max Act: 5.9843. Min Act: -0.1700
Data Index: 7232773 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #19