Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5701 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4379. Min Range: -6.4379
Max Act: 6.4379. Min Act: -0.1700
Data Index: 64204 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4379. Min Range: -6.4379
Max Act: 6.4379. Min Act: -0.1700
Data Index: 6776195 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4379. Min Range: -6.4379
Max Act: 6.4067. Min Act: -0.1700
Data Index: 4982911 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4379. Min Range: -6.4379
Max Act: 6.3754. Min Act: -0.1700
Data Index: 3767413 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4379. Min Range: -6.4379
Max Act: 6.3129. Min Act: -0.1700
Data Index: 3501771 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4379. Min Range: -6.4379
Max Act: 6.3129. Min Act: -0.1700
Data Index: 6357428 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4379. Min Range: -6.4379
Max Act: 6.2817. Min Act: -0.1700
Data Index: 177754 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4379. Min Range: -6.4379
Max Act: 6.2817. Min Act: -0.1700
Data Index: 6707199 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4379. Min Range: -6.4379
Max Act: 6.2504. Min Act: -0.1700
Data Index: 5098150 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4379. Min Range: -6.4379
Max Act: 6.2504. Min Act: -0.1700
Data Index: 2887629 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4379. Min Range: -6.4379
Max Act: 6.2817. Min Act: -0.1700
Data Index: 2251739 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4379. Min Range: -6.4379
Max Act: 6.2504. Min Act: -0.1700
Data Index: 3074694 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4379. Min Range: -6.4379
Max Act: 6.2192. Min Act: -0.1700
Data Index: 480734 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4379. Min Range: -6.4379
Max Act: 6.2192. Min Act: -0.1700
Data Index: 7889298 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4379. Min Range: -6.4379
Max Act: 6.2192. Min Act: -0.1700
Data Index: 5798504 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4379. Min Range: -6.4379
Max Act: 6.2192. Min Act: -0.1700
Data Index: 7661701 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4379. Min Range: -6.4379
Max Act: 6.2192. Min Act: -0.1700
Data Index: 3552692 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4379. Min Range: -6.4379
Max Act: 6.2192. Min Act: -0.1700
Data Index: 142336 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4379. Min Range: -6.4379
Max Act: 6.1879. Min Act: -0.1700
Data Index: 6108485 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4379. Min Range: -6.4379
Max Act: 6.1879. Min Act: -0.1700
Data Index: 413995 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #19