Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2938 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7255. Min Range: -7.7255
Max Act: 7.7255. Min Act: -0.1700
Data Index: 3007245 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7255. Min Range: -7.7255
Max Act: 7.7255. Min Act: -0.1700
Data Index: 7908357 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7255. Min Range: -7.7255
Max Act: 7.6630. Min Act: -0.1700
Data Index: 624515 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7255. Min Range: -7.7255
Max Act: 7.6317. Min Act: -0.1700
Data Index: 1926673 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7255. Min Range: -7.7255
Max Act: 7.5692. Min Act: -0.1700
Data Index: 5192198 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7255. Min Range: -7.7255
Max Act: 7.5067. Min Act: -0.1700
Data Index: 6250355 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7255. Min Range: -7.7255
Max Act: 7.5067. Min Act: -0.1700
Data Index: 1882406 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7255. Min Range: -7.7255
Max Act: 7.5067. Min Act: -0.1700
Data Index: 2404794 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7255. Min Range: -7.7255
Max Act: 7.4755. Min Act: -0.1700
Data Index: 7095502 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7255. Min Range: -7.7255
Max Act: 7.4442. Min Act: -0.1700
Data Index: 4329213 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7255. Min Range: -7.7255
Max Act: 7.4130. Min Act: -0.1700
Data Index: 1391951 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7255. Min Range: -7.7255
Max Act: 7.4130. Min Act: -0.1700
Data Index: 3164765 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7255. Min Range: -7.7255
Max Act: 7.4130. Min Act: -0.1700
Data Index: 1080201 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7255. Min Range: -7.7255
Max Act: 7.4130. Min Act: -0.1700
Data Index: 4700180 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7255. Min Range: -7.7255
Max Act: 7.3817. Min Act: -0.1700
Data Index: 7520239 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7255. Min Range: -7.7255
Max Act: 7.3505. Min Act: -0.1700
Data Index: 8793107 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7255. Min Range: -7.7255
Max Act: 7.3192. Min Act: -0.1700
Data Index: 334354 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7255. Min Range: -7.7255
Max Act: 7.3192. Min Act: -0.1700
Data Index: 2404787 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7255. Min Range: -7.7255
Max Act: 7.3192. Min Act: -0.1700
Data Index: 3873864 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7255. Min Range: -7.7255
Max Act: 7.3192. Min Act: -0.1700
Data Index: 6966112 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #19