Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3125 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1391. Min Range: -6.1391
Max Act: 6.1391. Min Act: -0.1700
Data Index: 6864810 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1391. Min Range: -6.1391
Max Act: 5.7953. Min Act: -0.1700
Data Index: 1400456 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1391. Min Range: -6.1391
Max Act: 5.6703. Min Act: -0.1700
Data Index: 5639782 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1391. Min Range: -6.1391
Max Act: 5.6391. Min Act: -0.1700
Data Index: 3561431 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1391. Min Range: -6.1391
Max Act: 5.6078. Min Act: -0.1700
Data Index: 1725955 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1391. Min Range: -6.1391
Max Act: 5.4516. Min Act: -0.1700
Data Index: 3632676 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1391. Min Range: -6.1391
Max Act: 5.4203. Min Act: -0.1700
Data Index: 3347167 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1391. Min Range: -6.1391
Max Act: 5.3891. Min Act: -0.1700
Data Index: 675709 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1391. Min Range: -6.1391
Max Act: 5.3891. Min Act: -0.1700
Data Index: 5566015 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1391. Min Range: -6.1391
Max Act: 5.3266. Min Act: -0.1700
Data Index: 428468 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1391. Min Range: -6.1391
Max Act: 5.3266. Min Act: -0.1700
Data Index: 3632671 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1391. Min Range: -6.1391
Max Act: 5.3266. Min Act: -0.1700
Data Index: 2890364 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1391. Min Range: -6.1391
Max Act: 5.3266. Min Act: -0.1700
Data Index: 7055182 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1391. Min Range: -6.1391
Max Act: 5.2953. Min Act: -0.1700
Data Index: 8114100 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1391. Min Range: -6.1391
Max Act: 5.2953. Min Act: -0.1700
Data Index: 7923926 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1391. Min Range: -6.1391
Max Act: 5.2953. Min Act: -0.1700
Data Index: 2613835 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1391. Min Range: -6.1391
Max Act: 5.2641. Min Act: -0.1700
Data Index: 4100090 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1391. Min Range: -6.1391
Max Act: 5.2328. Min Act: -0.1700
Data Index: 3011177 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1391. Min Range: -6.1391
Max Act: 5.2328. Min Act: -0.1700
Data Index: 8507506 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1391. Min Range: -6.1391
Max Act: 5.2016. Min Act: -0.1700
Data Index: 294090 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #19