Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4815 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8997. Min Range: -6.8997
Max Act: 6.8997. Min Act: -0.1700
Data Index: 3845964 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8997. Min Range: -6.8997
Max Act: 6.6497. Min Act: -0.1700
Data Index: 3459084 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8997. Min Range: -6.8997
Max Act: 6.5872. Min Act: -0.1700
Data Index: 5378675 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8997. Min Range: -6.8997
Max Act: 6.4310. Min Act: -0.1700
Data Index: 4498206 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8997. Min Range: -6.8997
Max Act: 6.3372. Min Act: -0.1700
Data Index: 7678393 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8997. Min Range: -6.8997
Max Act: 6.3685. Min Act: -0.1700
Data Index: 2672686 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8997. Min Range: -6.8997
Max Act: 6.3060. Min Act: -0.1700
Data Index: 6509912 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8997. Min Range: -6.8997
Max Act: 6.3060. Min Act: -0.1700
Data Index: 1270115 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8997. Min Range: -6.8997
Max Act: 6.3060. Min Act: -0.1700
Data Index: 3285388 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8997. Min Range: -6.8997
Max Act: 6.2747. Min Act: -0.1700
Data Index: 556521 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8997. Min Range: -6.8997
Max Act: 6.2435. Min Act: -0.1700
Data Index: 7782009 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8997. Min Range: -6.8997
Max Act: 6.2747. Min Act: -0.1700
Data Index: 1166149 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8997. Min Range: -6.8997
Max Act: 6.2122. Min Act: -0.1700
Data Index: 4192594 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8997. Min Range: -6.8997
Max Act: 6.1810. Min Act: -0.1700
Data Index: 7824151 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8997. Min Range: -6.8997
Max Act: 6.1810. Min Act: -0.1700
Data Index: 7433988 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8997. Min Range: -6.8997
Max Act: 6.1497. Min Act: -0.1700
Data Index: 3366449 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8997. Min Range: -6.8997
Max Act: 6.1497. Min Act: -0.1700
Data Index: 2863936 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8997. Min Range: -6.8997
Max Act: 6.1497. Min Act: -0.1700
Data Index: 5470215 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8997. Min Range: -6.8997
Max Act: 6.1497. Min Act: -0.1700
Data Index: 5308257 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8997. Min Range: -6.8997
Max Act: 6.1185. Min Act: -0.1700
Data Index: 5944768 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #19